# Divvun & Giellatekno - open source grammars for Sámi and other languages # Copyright © 2000-2013 The University of Tromsø # http://giellatekno.uit.no & http://divvun.no # # This program is free software; you can redistribute and/or modify # this file under the terms of the GNU General Public License as published by # the Free Software Foundation, either version 3 of the License, or # (at your option) any later version. The GNU General Public License # is found at http://www.gnu.org/licenses/gpl.html. It is # also available in the file $GTHOME/LICENSE.txt. # # Other licensing options are available upon request, please contact # giellatekno@hum.uit.no or divvun@hum.uit.no # ==================================================================== # # N O R T H E R N S Á M I D I S A M B I G U A T O R # ==================================================================== # # ==================================================================== # Sámi language technology project 2003-2013, University of Tromsø # # =============== # #!! !!!DELIMITERS # =============== # DELIMITERS = "<.>" "" "" "<...>" "<¶>"; #!! Sentence delimiters are the following: <.> <...> <¶> #PARENTHESES = "<$(>" "<$)>" "<$[>" "<$]>" "<${>" "<$}>" "<$«>" "<$»>" ; # ================== # #!! !!!TAGS AND SETS # ================== # SETS #!! !!Tags #!! This section lists all the tags inherited from the fst, and used as tags #!! in the syntactic analysis. The next section, __Sets__, contains sets defined #!! on the basis of the tags listed here, those set names are not visible in the output. # Tags declared as single-membered LISTs # ====================================== #!! !Beginning and end of sentence LIST BOS = (>>>) (~~) ; #!! BOS LIST EOS = (<<<) (~~) ; #!! EOS # We define end of clause and beginning of clause in a way so that the file # may be read both by the CG-2 and the vislcg formalisms. # CG3 doesn´t function without >>> and <<< ! #!! !Parts of speech tags LIST N = N ; #!! N LIST A = A ; #!! A LIST Adv = Adv ; #!! Adv LIST V = V ; #!! V LIST Pron = Pron ; #!! Pron LIST CS = CS ; #!! CS LIST CC = CC ; #!! CC SET CC-CS = CC OR CS ; LIST Po = Po ; #!! Po LIST Pr = Pr ; #!! Pr LIST Pcle = Pcle ; #!! Pcle LIST Num = Num ; #!! Num LIST Interj = Interj ; #!! Interj LIST ABBR = ABBR ; #!! ABBR LIST ACR = ACR ; #!! ACR LIST CLB = CLB ; #!! CLB LIST LEFT = LEFT ; #!! LEFT LIST RIGHT = RIGHT ; #!! RIGHT LIST WEB = WEB ; #!! WEB LIST QMARK = """ ; # " LIST PPUNCT = PUNCT ; #!! PUNCT SET PUNCT = PPUNCT - QMARK ; LIST COMMA = "," ; LIST ¶ = ¶; #LIST V* = V* ; #!! !Tags for POS sub-categories LIST Pers = Pers ; #!! Pers LIST Dem = Dem ; #!! Dem LIST Interr = Interr ; #!! Interr LIST Indef = Indef ; #!! Indef LIST Recipr = Recipr ; #!! Recipr LIST Refl = Refl ; #!! Refl LIST Rel = Rel ; #!! Rel LIST Coll = Coll ; #!! Coll LIST NomAg = NomAg ; #!! NomAg LIST G3 = G3 ; #!! G3 LIST Prop = Prop ; #!! Prop #!! !Tags for morphosyntactic properties LIST Nom = Nom ; #!! Nom LIST Acc = Acc ; #!! Acc LIST Gen = Gen ; #!! Gen LIST Ill = Ill ; #!! Ill LIST Loc = Loc ; #!! Loc LIST Com = Com ; #!! Com LIST Ess = Ess ; #!! Ess LIST Sg = Sg ; #!! Sg LIST Du = Du ; #!! Du LIST Pl = Pl ; #!! Pl LIST RCmpnd = RCmpnd ; #!! RCmpnd LIST Cmpnd = Cmpnd ; #!! Cmpnd LIST SgNomCmp = SgNomCmp ; #!! SgNomCmp LIST SgGenCmp = SgGenCmp ; #!! SgGenCmp LIST ShCmp = ShCmp ; #!! ShCmp LIST PxSg1 = PxSg1 ; #!! PxSg1 LIST PxSg2 = PxSg2 ; #!! PxSg2 LIST PxSg3 = PxSg3 ; #!! PxSg3 LIST PxDu1 = PxDu1 ; #!! PxDu1 LIST PxDu2 = PxDu2 ; #!! PxDu2 LIST PxDu3 = PxDu3 ; #!! PxDu3 LIST PxPl1 = PxPl1 ; #!! PxPl1 LIST PxPl2 = PxPl2 ; #!! PxPl2 LIST PxPl3 = PxPl3 ; #!! PxPl3 LIST Comp = Comp ; #!! Comp LIST Superl = Superl ; #!! Superl LIST Attr = Attr ; #!! Attr LIST Ord = Ord ; #!! Ord LIST Qst = Qst ; #!! Qst LIST IV = IV ; #!! IV LIST TV = TV ; #!! TV LIST Prt = Prt; #!! Prt LIST Prs = Prs ; #!! Prs LIST Ind = Ind ; #!! Ind LIST Pot = Pot ; #!! Pot LIST Cond = Cond ; #!! Cond LIST Imprt = Imprt ; #!! Imprt LIST ImprtII = ImprtII ; #!! ImprtII LIST Sg1 = Sg1 ; #!! Sg1 LIST Sg2 = Sg2 ; #!! Sg2 LIST Sg3 = Sg3 ; #!! Sg3 LIST Du1 = Du1 ; #!! Du1 LIST Du2 = Du2 ; #!! Du2 LIST Du3 = Du3 ; #!! Du3 LIST Pl1 = Pl1 ; #!! Pl1 LIST Pl2 = Pl2 ; #!! Pl2 LIST Pl3 = Pl3 ; #!! Pl3 LIST Inf = Inf ; #!! Inf LIST ConNeg = ConNeg ; #!! ConNeg LIST Neg = Neg ; #!! Neg LIST PrfPrc = PrfPrc ; #!! PrfPrc LIST VGen = VGen ; #!! VGen LIST PrsPrc = PrsPrc ; #!! PrsPrc LIST Ger = Ger ; #!! Ger LIST Sup = Sup ; #!! Sup LIST Actio = Actio ; #!! Actio LIST VAbess = VAbess ; #!! # The ("ge" Pcle) etc. are used in Apertium #!! !Tags for clitic particles LIST Foc/ge = Foc/ge ("ge" Pcle) ; #!! Foc/ge LIST Foc/gen = Foc/gen ("gen" Pcle) ; #!! Foc/gen LIST Foc/ges = Foc/ges ("ges" Pcle) ; #!! Foc/ges LIST Foc/gis = Foc/gis ("gis" Pcle) ; #!! Foc/gis LIST Foc/naj = Foc/naj ("naj" Pcle) ; #!! Foc/naj LIST Foc/ba = Foc/ba ("ba" Pcle) ; #!! Foc/ba LIST Foc/be = Foc/be ("be" Pcle) ; #!! Foc/be LIST Foc/hal = Foc/hal ("hal" Pcle) ; #!! Foc/hal LIST Foc/han = Foc/han ("han" Pcle) ; #!! Foc/han LIST Foc/bat = Foc/bat ("bat" Pcle) ; #!! Foc/bat LIST Foc/son = Foc/son ("sun" Pcle) ; #!! Foc/son #!! !Derivation tags LIST Der/PassL = Der/PassL ; LIST Der/Pass = Der/Pass ; #!! Der/PassL Der/PassS LIST Der/NomAg = Der/NomAg ; #!! Der/NomAg LIST Actor = NomAg Der/NomAg ; #!! NomAg LIST Der/adda = Der/adda ; #!! Der/adda LIST Der/ahtti = Der/ahtti ; #!! Der/ahtti LIST Der/alla = Der/alla ; #!! Der/alla LIST Der/asti = Der/asti ; #!! Der/asti LIST Der/easti = Der/easti ; #!! Der/easti LIST Der/d = Der/d ; #!! Der/d LIST Der/eaddji = Der/eaddji ; #!! Der/eaddji LIST Der/eamoš = Der/eamoš ; #!! Der/eamoš LIST Der/amoš = Der/amoš ; #!! Der/amoš LIST Der/geahtes = Der/geahtes ; #!! Der/geahtes LIST Der/gielat = Der/gielat ; #!! Der/gielat LIST Der/NuA = Der/NuA ; #!! Der/NuA (what is NuA?) LIST Der/h = Der/h ; #!! Der/h LIST Der/heapmi = Der/heapmi ; #!! Der/heapmi LIST Der/hudda = Der/hudda ; #!! Der/hudda LIST Der/huhtti = Der/huhtti ; #!! Der/huhtti LIST Der/huvva = Der/huvva ; #!! Der/huvva LIST Der/halla = Der/halla ; #!! Der/halla LIST Der/j = Der/j ; #!! Der/j LIST Der/l = Der/l ; #!! Der/l LIST Der/laš = Der/lâš ; #!! Der/laš LIST Der/las = Der/las ; #!! Der/las LIST Der/hat = Der/hat ; #!! Der/hat LIST Der/mállet = Der/mállet ; #!! Der/mállet LIST Der/meahttun = Der/meahttun ; #!! Der/meahttun LIST Der/muš = Der/muš ; #!! Der/muš LIST Der/NomAct = Der/NomAct ; #!! Der/NomAct LIST Der/st = Der/st ; #!! Der/st LIST Der/stuvva = Der/stuvva ; #!! Der/stuvva LIST Der/upmi = Der/upmi ; #!! Der/upmi LIST Der/supmi = Der/supmi ; #!! Der/supmi LIST Der/vuohta = Der/vuotâ ; #!! Der/vuotâ LIST Der/goahti = Der/kyetti ; #!! Der/kyetti LIST Der/lágan = Der/lagan ; #!! Der/lagan LIST Der/lágán = Der/lágán ; #!! Der/lágán LIST Der/lágaš = Der/lágaš ; #!! Der/lágaš LIST Der/jagáš = Der/jagáš ; #!! Der/jagáš LIST Der/jahkásaš = Der/jahkásaš ; #!! Der/jahkásaš LIST Der/diibmosaš = Der/diibmosaš ; #!! Der/diibmosaš LIST Der/dássásaš = Der/dássásaš ; #!! Der/dássásaš LIST Der/A = Der/A ; #!! Der/A LIST Der/Dimin = Der/Dimin ; #!! Der/Dimin LIST Der/viđá = Der/viđá ; #!! Der/viđá LIST Der/viđi = Der/viđi ; #!! Der/viđi LIST Der/veara = Der/veara ; #!! Der/veara LIST Der/duohke = Der/duohke ; #!! Der/duohke LIST Der/duohkai = Der/duohkai ; #!! Der/duohkai LIST Der/vuolle = Der/vuolle ; #!! Der/vuolle LIST Der/vuollai = Der/vuollai ; #!! Der/vuollai LIST Der/vuolde = Der/vuolde ; #!! Der/vuolde LIST = ; #!! #!! !Semantic tags LIST Sem/Act = Sem/Act Sem/Act_Group Sem/Act_Plc Sem/Act_Route; #Activity #Ollet guhká dainna X-Com (Veaigin bisánasttii Ristenge geahččat, man guhkás Lemet-gázzi juo ledje ollen dainna divvunbargguin.) # bargu LIST Sem/Amount = Sem/Amount Sem/Amount_Build Sem/Amount_Semcon; LIST Sem/Ani = Sem/Ani Sem/Ani_Body-abstr_Hum Sem/Body Sem/Body-abstr Sem/Body-abstr_Prod-audio_Semcon Sem/Body_Body-abstr Sem/Body_Clth Sem/Body_Food Sem/Body_Group_Hum Sem/Body_Hum Sem/Body_Mat Sem/Body_Measr Sem/Body_Obj_Tool-catch Sem/Body_Plc Sem/Body_Time ; #Animal #bivdit X-Loc veahki. LIST Sem/Aniprod = Sem/Aniprod Sem/Aniprod_Hum Sem/Aniprod_Obj-clo Sem/Aniprod_Perc-phys Sem/Aniprod_Plc ; LIST Sem/Body = Sem/Body Sem/Body_Body-abstr Sem/Body_Clth Sem/Body_Food Sem/Body_Group_Hum Sem/Body_Hum Sem/Body_Mat Sem/Body_Measr Sem/Body_Obj_Tool-catch Sem/Body_Plc Sem/Body_Time ; #Body #Buohkat ceggejedje gieđa. Mon gal attán dutnje bealji vuollái. Go duos dás speččohallá bahtii de gal buollá bargomokta! Čuolda basttii sus alemii. LIST Sem/Body-abstr = Sem/Ani_Body-abstr_Hum Sem/Body-abstr Sem/Body-abstr_Prod-audio_Semcon Sem/Body_Body-abstr ; # jierbmi, siellu, ... LIST Sem/Build = Sem/Amount_Build Sem/Ani_Build Sem/Ani_Build_Hum_Txt Sem/Build Sem/Build_Build-part Sem/Build_Clth-part Sem/Build_Edu_Org Sem/Build_Event_Org Sem/Build_Org Sem/Build_Route ; #Build #Sem #Syn: hukset X deike LIST Sem/Build-part = Sem/Ani_Build-part Sem/Build-part Sem/Build-part_Plc Sem/Build_Build-part ; #Building part, e.g. room #Sem:+con,+count,-mova #Syn: mannat X sisa LIST Sem/Cat = Sem/Cat ; LIST Sem/Clth = Sem/Body_Clth Sem/Clth Sem/Clth_Hum ; #Clothes #Sem #bidjat X ala/badjelii. LIST Sem/Clth-jewl = Sem/Clth-jewl Sem/Clth-jewl_Curr Sem/Clth-jewl_Money Sem/Clth-jewl_Plant Sem/Org_Clth-jewl Sem/Clth-jewl_Org ; #Clothes jewelry #Synt: bidjat X ala. *bidjat X badjelii. LIST Sem/Clth-part = Sem/Build_Clth-part Sem/Clth-part ; LIST Sem/Ctain = Sem/Ctain Sem/Ctain_Feat-phys Sem/Ctain_Furn Sem/Ctain_Tool Sem/Ctain_Tool-measr ; #Container #Sem:+mova #Syn: bidjat juoidá X sisa LIST Sem/Ctain-abstr = Sem/Ctain-abstr Sem/Ctain-abstr_Org ; LIST Sem/Ctain-clth = Sem/Ctain-clth Sem/Ctain-clth_Plant Sem/Ctain-clth_Veh ; LIST Sem/Curr = Sem/Clth-jewl_Curr Sem/Curr Sem/Curr_Org; #Syn: Mun mávssan dasa 100 X. Dat máksá 100 X. LIST Sem/Date = Sem/Date ; LIST Sem/Dance = Sem/Dance Sem/Dance_Org Sem/Dance_Prod-audio ; #Ollugat dánso swinga lávddi ovddabeale. LIST Sem/Dir = Sem/Dir ; LIST Sem/Domain = Sem/Domain Sem/Domain_Food-med Sem/Domain_Prod-audio; LIST Sem/Drink = Sem/Drink ; LIST Sem/Edu = Sem/Build_Edu_Org Sem/Edu Sem/Edu_Event Sem/Edu_Group_Hum Sem/Edu_Mat Sem/Edu_Org ; # vázzit X-Acc. addit X-Acc. X:s lea beroštupmi. LIST Sem/Event = Sem/Build_Event_Org Sem/Edu_Event Sem/Event Sem/Event_Food Sem/Event_Hum Sem/Event_Plc Sem/Event_Time ; # X maŋŋel mun ferten vuolgit. X:s leat ollu olbmot. *Lean leamaš doppe X:Gen. #LIST Sem/Feat-cogn = Sem/Feat-cogn ; # oaidnu, oamedovdu, viissisvuohta #LIST Sem/Feat-phys = Sem/Feat-phys ; # oaidnu LIST Sem/Feat = Sem/Feat Sem/Feat_Plant ; #many -vuohta and -dat nouns LIST Sem/Feat-measr = Sem/Feat-measr ; LIST Sem/Feat-phys = Sem/Ctain_Feat-phys Sem/Feat-phys Sem/Feat-phys_Tool-write Sem/Feat-phys_Veh Sem/Feat-phys_Wthr ; LIST Sem/Feat-psych = Sem/Feat-psych Sem/Feat-psych_Hum ; #not touchable, not countable ("beroštupmi" "gáđašvuohta" "mokta" "sáhkkiivuohta") - Mus lea X, Son lea X-adj persovdna # muitu LIST Sem/Fem = Sem/Fem ; LIST Sem/Food = Sem/Body_Food Sem/Event_Food Sem/Food Sem/Food_Perc-phys Sem/Food_Plant ; #Syn: bassit/borrat/sohpat X-Acc. mon im læk borram dam guolest. mun boran iđitbiepmu. mus lea iđitbiebmu fárus. birgui borastuvvat LIST Sem/Food-med = Sem/Domain_Food-med Sem/Food-med ; LIST Sem/Furn = Sem/Ctain_Furn Sem/Furn ; #Syn: bidjat X vissui: čohkkedit X ala LIST Sem/Game = Sem/Game Sem/Game_Obj-play ; LIST Sem/Geom = Sem/Geom Sem/Geom_Obj ; LIST Sem/Group = Sem/Act_Group Sem/Ani_Group Sem/Ani_Group_Hum Sem/Body_Group_Hum Sem/Edu_Group_Hum Sem/Group Sem/Group_Hum Sem/Group_Hum_Org Sem/Group_Hum_Plc Sem/Group_Hum_Prod-vis Sem/Group_Org Sem/Group_Sign Sem/Group_Txt ; #Bárdni lea riggámus sogas. -Plc LIST Sem/Hum = Sem/Ani_Body-abstr_Hum Sem/Ani_Build_Hum_Txt Sem/Ani_Group_Hum Sem/Ani_Hum Sem/Ani_Hum_Plc Sem/Ani_Hum_Time Sem/Aniprod_Hum Sem/Body_Group_Hum Sem/Body_Hum Sem/Clth_Hum Sem/Edu_Group_Hum Sem/Event_Hum Sem/Feat-psych_Hum Sem/Group_Hum Sem/Group_Hum_Org Sem/Group_Hum_Plc Sem/Group_Hum_Prod-vis Sem/Hum Sem/Hum_Lang Sem/Hum_Lang_Plc Sem/Hum_Lang_Time Sem/Hum_Obj Sem/Hum_Org Sem/Hum_Plant Sem/Hum_Plc Sem/Hum_Tool Sem/Hum_Veh Sem/Hum_Wthr ; #Human #LIST Sem/Hum-kin = Sem/Hum-kin ; #Human kinship LIST Sem/Hum-abstr = Sem/Hum-abstr ; LIST Sem/Ideol = Sem/Ideol ; LIST Sem/Lang = Sem/Lang ; #Syn: hállat X:illatiiva. Son hállá X:Acc. Jorgalan dán X:lokatiiva Y:illatiiva. LIST Sem/Mal = Sem/Mal ; LIST Sem/Mat = Sem/Body_Mat Sem/Edu_Mat Sem/Mat Sem/Mat_Plant Sem/Mat_Txt ; # Material #Sem: cannot pass through it without destroying it, ráhkadit juoidá X:s. Niibi lea X-Loc-Sg. #Dán báhkis šaddá čáppa gohppu. LIST Sem/Measr = Sem/Body_Measr Sem/Measr Sem/Measr_Time ; # Lea lassánan 100 X-Loc. LIST Sem/Money = Sem/Clth-jewl_Money Sem/Money Sem/Money_Obj Sem/Money_Txt ; #Mun mávssán X. Mii ávžžuhit vuovdit alimus X-Ill (haddái). ruhtadit doaibmabušeahtain. vuovdit/bidjat ruđast - selge for penger LIST Sem/Obj = Sem/Body_Obj_Tool-catch Sem/Geom_Obj Sem/Hum_Obj Sem/Money_Obj Sem/Obj Sem/Obj_Semcon Sem/Obj_State ; # concrete object, movable #Syn: Mun guoskkán X-Acc. Dá livčče dutnje X-Nom (sabehat). čievččastit geađggi johkii #LIST Sem/Obj-com = Sem/Obj-com ; #communication object #hálan telefuvnnas/e-poasttas #sádden X bokte LIST Sem/Obj-clo = Sem/Aniprod_Obj-clo Sem/Obj-clo ; #bidjat juoidá Obj-clo sisa LIST Sem/Obj-cogn = Sem/Obj-cogn ; LIST Sem/Obj-el = Sem/Obj-el ; # moveable, countable, touchable, electrical objects that can be turned on and of, mus lea X alde, mun bijan X ala LIST Sem/Obj-ling = Sem/Obj-ling ; LIST Sem/Obj-play = Sem/Obj-play Sem/Game_Obj-play Sem/Obj-play_Sport ; LIST Sem/Obj-rope = Sem/Obj-rope ; LIST Sem/Obj-surfc = Sem/Obj-surfc ; LIST Sem/Org = Sem/Build_Edu_Org Sem/Build_Event_Org Sem/Build_Org Sem/Ctain-abstr_Org Sem/Curr_Org Sem/Dance_Org Sem/Edu_Org Sem/Group_Hum_Org Sem/Group_Org Sem/Hum_Org Sem/Org Sem/Org_Clth-jewl Sem/Org_Rule Sem/Org_Txt Sem/Org_Veh Sem/Clth-jewl_Org ; LIST Sem/Part = Sem/Part Sem/Part_Prod-cogn ; # bealli, oassi LIST Sem/Perc-cogn = Sem/Perc-cogn ; LIST Sem/Perc-emo = Sem/Perc-emo ; #Sem not touchable, not countable ("ballu" "suhttu" "vaši") - Mun dovddan garra X. Mun lean X+Loc # moraš LIST Sem/Perc-phys = Sem/Aniprod_Perc-phys Sem/Food_Perc-phys Sem/Perc-phys Sem/Perc-emo_Wthr ; # anistupmi, oaidnu LIST Sem/Perc-psych = Sem/Perc-psych ; LIST Sem/Plant = Sem/Clth-jewl_Plant Sem/Ctain-clth_Plant Sem/Feat_Plant Sem/Food_Plant Sem/Hum_Plant Sem/Mat_Plant Sem/Plant Sem/Plant_Tool Sem/Plant_Tool-measr ; #čáhccet X-Acc #X-Nom šaddet LIST Sem/Plant-part = Sem/Plant_Plant-part Sem/Plant-part ; #čáhccet X-Acc #X-Nom šaddet LIST Sem/Plc = Sem/Act_Plc Sem/Ani_Hum_Plc Sem/Ani_Plc Sem/Ani_Plc_Txt Sem/Aniprod_Plc Sem/Body_Plc Sem/Build-part_Plc Sem/Event_Plc Sem/Group_Hum_Plc Sem/Hum_Lang_Plc Sem/Hum_Plc Sem/Plc Sem/Plc_Pos Sem/Plc_Route Sem/Plc_Substnc Sem/Plc_Substnc_Wthr Sem/Plc_Time Sem/Plc_Tool-catch Sem/Plc_Wthr; LIST Sem/Plc-abstr = Sem/Plc-abstr Sem/Plc-abstr_Rel_State Sem/Plc-abstr_Route ; LIST Sem/Plc-elevate = Sem/Plc-elevate ; LIST Sem/Plc-line = Sem/Plc-line ; LIST Sem/Plc-water = Sem/Plc-water ; LIST Sem/Pos = Sem/Plc_Pos Sem/Pos ; #Social position (job etc.) LIST Sem/Process = Sem/Process ; LIST Sem/Prod = Sem/Prod ; #jáhkku LIST Sem/Prod-audio = Sem/Body-abstr_Prod-audio_Semcon Sem/Dance_Prod-audio Sem/Domain_Prod-audio Sem/Prod-audio Sem/Prod-audio_Txt ; #attáldat LIST Sem/Prod-cogn = Sem/Part_Prod-cogn Sem/Prod-cogn Sem/Prod-cogn_Txt ; # muittuhus, ipmárdus, jáhkku, osku, vuordámuš, viisodat? diehtu? LIST Sem/Prod-ling = Sem/Prod-ling ; LIST Sem/Prod-vis = Sem/Group_Hum_Prod-vis Sem/Prod-vis ; LIST Sem/Rel = Sem/Plc-abstr_Rel_State Sem/Rel ; LIST Sem/Route = Sem/Act_Route Sem/Build_Route Sem/Plc-abstr_Route Sem/Plc_Route Sem/Route ; LIST Sem/Rule = Sem/Org_Rule Sem/Rule ; LIST Sem/Semcon = Sem/Amount_Semcon Sem/Body-abstr_Prod-audio_Semcon Sem/Obj_Semcon Sem/Semcon Sem/Semcon_Txt ; # semantic concept LIST Sem/Sign = Sem/Group_Sign Sem/Sign ; LIST Sem/Sport = Sem/Obj-play_Sport Sem/Sport ; LIST Sem/State = Sem/Plc-abstr_Rel_State Sem/State Sem/Obj_State ; # lihkku, ipmilbalolašvuohta, mokta, váivi, váttisvuohta LIST Sem/State-sick = Sem/State-sick ; LIST Sem/Substnc = Sem/Plc_Substnc Sem/Plc_Substnc_Wthr Sem/Substnc Sem/Substnc_Wthr ; #Sem: can pass through it without destroying it LIST Sem/Sur = Sem/Sur ; LIST Sem/Symbol = Sem/Symbol ; LIST Sem/Time = Sem/Ani_Hum_Time Sem/Ani_Time Sem/Body_Time Sem/Event_Time Sem/Hum_Lang_Time Sem/Measr_Time Sem/Plc_Time Sem/Time Sem/Time_Wthr ; LIST Sem/Tool = Sem/Ctain_Tool Sem/Hum_Tool Sem/Lang_Tool Sem/Plant_Tool Sem/Tool ; LIST Sem/Tool-catch = Sem/Body_Obj_Tool-catch Sem/Plc_Tool-catch Sem/Tool-catch ; LIST Sem/Tool-clean = Sem/Tool-clean ; LIST Sem/Tool-it = Sem/Tool-it ; LIST Sem/Tool-measr = Sem/Ctain_Tool-measr Sem/Plant_Tool-measr Sem/Tool-measr ; LIST Sem/Tool-music = Sem/Tool-music ; LIST Sem/Tool-write = Sem/Feat-phys_Tool-write Sem/Tool-write ; LIST Sem/Txt = Sem/Ani_Build_Hum_Txt Sem/Ani_Plc_Txt Sem/Group_Txt Sem/Mat_Txt Sem/Money_Txt Sem/Org_Txt Sem/Prod-audio_Txt Sem/Prod-cogn_Txt Sem/Semcon_Txt Sem/Txt ; #Syn: Čále dearvvuođaidat guossegirjámet! # das čuožžu LIST Sem/Veh = Sem/Ani_Veh Sem/Ctain-clth_Veh Sem/Feat-phys_Veh Sem/Hum_Veh Sem/Org_Veh Sem/Veh ; #Syn: Vuolggán X:Com #LIST Sem/Veh-cntain = Sem/Veh-cntain ; #Manan X sisa. #vuolggán X:Com. LIST Sem/Wthr = Sem/Feat-phys_Wthr Sem/Hum_Wthr Sem/Perc-emo_Wthr Sem/Plc_Substnc_Wthr Sem/Plc_Wthr Sem/Substnc_Wthr Sem/Time_Wthr Sem/Wthr ; #Sem: Birget X:Ess. jietna gullui X-Loc (balvvas). Olgun/Odne lea + Wthr-Nom. ?Man ollu lea Wthr-Nom? Wthr-Gen maŋŋel boahtá X. Makkár lea dálki/siivu? #Ex: árvi, borga, muohtá, čoaskadálki, baján, bievla, bodnejiekŋa, bivdodálki, gasis, guoldu LIST Sem/Wpn = Sem/Wpn ; #oaggut oaggunstákkuin, goddit X+Com LIST Sem/Date = Sem/Date ; LIST Sem/Year = Sem/Year ; SET FIRSTNAME = (Prop Sem/Fem) OR (Prop Sem/Mal) ; SET TIME-N-SET = N + Sem/Time ; LIST NOT-TIME = "dulvi" "lohpi" "vuorru" ; SET TIME-N = TIME-N-SET - NOT-TIME ; #!! ! Syntactic tags LIST @+FAUXV = @+FAUXV ; #!! @+FAUXV LIST @+FMAINV = @+FMAINV ; #!! @+FMAINV LIST @-FAUXV = @-FAUXV ; #!! @-FAUXV LIST @-FMAINV = @-FMAINV ; #!! @-FMAINV LIST @-FSUBJ> = @-FSUBJ> ; #!! @-FSUBJ> LIST @-F = @-FOBJ> ; #!! @-FOBJ> LIST @SPRED = @-FADVL> ; #!! @-FADVL> LIST @-F = @-FSPRED> ; #!! @-FSPRED> LIST @-FOPRED> = @-FOPRED> ; #!! @-FOPRED> SET FOBJ = @-F ; SET FMAINV = @-FMAINV OR @+FMAINV ; SET FAUXV = @-FAUXV OR @+FAUXV ; LIST @>ADVL = @>ADVL ; #!! @>ADVL LIST @ADVL< = @ADVL< ; #!! @ADVL< LIST @ = @ADVL> ; #!! @ADVL> LIST ADVL = @ADVL @ADVL> @ADVL< @ADVL @-F ; #!! @ADVL LIST @HAB> = @HAB> ; #!! @HAB> LIST @ ; LIST @>N = @>N ; #!! @>N LIST @>Interj = @>Interj ; #!! @>Interj LIST @N< = @N< ; #!! @N< LIST @>A = @>A ; #!! @>A LIST @P< = @P< ; #!! @P< LIST @>P = @>P ; #!! @>P LIST @HNOUN = @HNOUN ; #!! @HNOUN LIST @INTERJ = @INTERJ ; #!! @INTERJ LIST @>Num = @>Num; #!! @>Num LIST @Pron< = @Pron< ; #!! @Pron< LIST @>Pron = @>Pron ; #!! @>Pron LIST @Num< = @Num< ; #!! @Num< LIST @OBJ = @OBJ ; #!! @OBJ LIST @ = @OBJ> ; #!! @OBJ> LIST @OPRED = @OPRED ; #!! @OPRED LIST @ = @OPRED> ; #!! @OPRED> LIST @PCLE = @PCLE ; #!! @PCLE LIST @COMP-CS< = @COMP-CS< ; #!! @COMP-CS< LIST @SPRED = @SPRED ; #!! @SPRED LIST @ = @SPRED> ; #!! @SPRED> LIST @SUBJ = @SUBJ ; #!! @SUBJ LIST @ = @SUBJ> ; #!! @SUBJ> SET SUBJ = @ OR @SUBJ ; SET SPRED = @ OR @SPRED ; SET OPRED = @ OR @OPRED ; LIST @PPRED = @PPRED ; #!! @PPRED LIST @APP = @APP ; #!! @APP LIST @APP-N< = @APP-N< ; #!! @APP-N< LIST @APP-Pron< = @APP-Pron< ; #!! @APP-Pron< LIST @APP>Pron = @APP>Pron ; #!! @APP>Pron LIST @APP-Num< = @APP-Num< ; #!! @APP-Num< LIST @APP-ADVL< = @APP-ADVL< ; #!! @APP-ADVL< LIST @VOC = @VOC ; #!! @VOC LIST @CVP = @CVP ; #!! @CVP LIST @CNP = @CNP ; #!! @CNP SET OBJ = (@) OR (@OBJ) OR (@-F) ; LIST = @OBJ> @-FOBJ> ; SET -OTHERS = OBJ> OR (Gen) OR (Nom) OR (Ess) OR (Loc) OR (Adv) ; SET NOT-FAUXV = FMAINV OR OBJ + V OR ADVL + V ; # Works after the mapping rules for verbs. SET SYN-V = FMAINV OR FAUXV OR V + SUBJ OR OBJ + V OR ADVL + V OR (V @>N) OR (V @N<) OR (V @A<) ; LIST @X = @X ; #!! @X # ======== SETS # ======== #!! !!Sets containing sets of lists and tags #!! This part of the file lists a large number of sets based partly upon the tags defined above, and #!! partly upon lexemes drawn from the lexicon. #!! See the sourcefile itself to inspect the sets, what follows here is an overview of the set types. #!! !Sets for Single-word sets #!! OKTA and go, and the set INITIAL for initial letters LIST OKTA = "ohtâ"; #!! OKTA LIST go = "go" ; #!! go LIST INITIAL = "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z" "á" "æ" "ø" "å" "ö" "ä" ; #!! INITIAL #!! !Sets for word or not LIST WORD = N A Adv V Pron CS CC Po Pr Interj Pcle Num ABBR ACR \? ; #!! WORD # any word SET REAL-WORD = WORD - Num - Ord ; #!! REAL-WORD SET REAL-WORD-NOT-ABBR = WORD - Num - Ord - (ABBR N) ; # This is former REALWORD-NOTABBR #!! REAL-WORD-NOT-ABBR SET WORD-NOT-de = WORD - ("de") ; #!! WORD-NOT-de SET NOT-COMMA = WORD - COMMA ; #!! NOT-COMMA # Note! We also have CLB_NOT-COMMA #!! !Derivational affixes LIST DER-V = Der/adda Der/alla Der/asti Der/d Der/g Der/h Der/halla Der/hudda Der/huhtti Der/huvva Der/j Der/l Der/ahtti Der/st Der/stuvva Der/goahti ; #!! DER-V LIST DER-N = Der/Dimin Der/eamoš Der/heapmi Der/NomAct Der/š Der/muš Der/upmi Der/us Der/vuohta Der/NomAg Der/NomAct ; #!! DER-N LIST DER-A1 = Der/diibmosaš Der/vuovttat Der/čalmmat Der/dássásaš Der/eaddji Der/geahtes Der/keahtes Der/heapmi Der/jahkásaš Der/lágan Der/lágaš Der/laš Der/meahttun Der/lágán Der/gielat Der/mállet Der/kultuvrrat (V* A) Der/A Der/A* ; #!! DER-A1 SET DER-A = DER-A1 - Adv ; #!! DER-A LIST A-V = (V* A) ; #!! A-V SET A-NOT-V = A - A-V ; #!! A-NOT-V #!! !Case sets # --------- LIST ADVLCASE = Ill Loc Com Ess ; #!! ADLVCASE # Sg Nom - Sg Nom | Pl Nom - Pl Nom # Sg Acc - Sg Acc | Pl Acc - Pl Acc # Sg Gen - Sg Gen | Pl Gen - Pl Gen # Sg Gen - Sg Ill | Pl Gen/Ill - Pl Ill # Sg Gen - Sg Loc | Pl Loc - Pl Loc # Sg Com - Sg Com | Pl Gen/Com - Pl Com # Ess - Ess LIST CASE-HALFAGREEMENT = Ill (Sg Loc) (Pl Com) Ess ; #!! CASE-HALFAGREEMENT LIST CASE-AGREEMENT = Nom Acc Gen (Pl Ill) Loc Com Ess ; #!! CASE-AGREEMENT LIST CASE = Nom Acc Gen Ill Loc Com Ess ; #!! CASE SET NOT-NOM = CASE - Nom ; #!! NOT-NOM SET NOT-GEN = CASE - Gen ; #!! NOT-GEN SET NOT-ACC = CASE - Acc ; #!! NOT-ACC #!! !Verb sets # --------- # Verbs and their complements # - - - - - - - - - - - - - - SET NOT-V = WORD - V ; #!! NOT-V #!! !Sets for finiteness and mood # - - - - - - - - - - SET REAL-NEG = Neg - Sup ; #!! REAL-NEG SET MOOD-V = Ind OR Pot OR Imprt OR ImprtII OR Cond OR (Neg Sup) ; #!! MOOD-V LIST GC = ("gč") ; #!! GC SET VFIN = GC OR MOOD-V - ConNeg ; #!! VFIN SET VFIN-POS = MOOD-V - ConNeg - Neg ; #!! VFIN-POS SET VFIN-NOT-IMPRT = VFIN - Imprt ; #!! VFIN-NOT-IMPRT SET VFIN-NOT-NEG = VFIN - Neg ; #!! VFIN-NOT-NEG # this might be to strict, besides, 'iige' can be written 'ii ge' SET NOT-PRFPRC = WORD - PrfPrc ; #!! NOT-PRFPRC #!! !Sets for person # - - - - LIST SG1-V = (V Sg1) ; LIST SG2-V = (V Sg2) ; LIST SG3-V = (V Sg3) ; LIST DU1-V = (V Du1) ; LIST DU2-V = (V Du2) ; LIST DU3-V = (V Du3) ; LIST PL1-V = (V Pl1) ; LIST PL2-V = (V Pl2) ; LIST PL3-V = (V Pl3) ; SET POSITIVE-V = SG1-V OR SG2-V OR SG3-V OR DU1-V OR DU2-V OR DU3-V OR PL1-V OR PL2-V OR PL3-V ; # Note that imperative verbs are not included in these sets! # Some subsets of the VFIN sets # - - - - - - - - - - - - - - - SET SG-V = SG1-V OR SG2-V OR SG3-V ; SET DU-V = DU1-V OR DU2-V OR DU3-V ; SET PL-V = PL1-V OR PL2-V OR PL3-V ; SET DU-PL-V = DU1-V OR DU2-V OR DU3-V OR PL1-V OR PL2-V OR PL3-V ; SET 1-2-V = SG1-V OR SG2-V OR DU1-V OR DU2-V OR PL1-V OR PL2-V ; #!! !Sets consisting of forms of "leđe" (these ones need to be rewritten) # - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - SET LEAN = ("leđe" Prs Sg1) + Ind OR ("leđe" V Prt ConNeg); SET LEAT = ("leđe" Prs Pl1) + Ind OR ("leđe" V Prs Pl3) + Ind OR ("leđe" V Prs Sg2) + Ind OR ("leđe" V Inf) OR ("leđe" V Prs ConNeg) + Ind ; SET LEAT-FIN-NOT-IMPRT = ("leđe" V) - Imprt; LIST PRFPRC-V = (V PrfPrc) ; LIST LEATPRFPRC = ("leđe" PrfPrc) ; SET PRC-NOT-LEAT = PRFPRC-V - LEATPRFPRC ; # In order to distinguish between real leat-constructions and participles of other verbs LIST HABEO-SG3 = ("leđe" Sg3) (V Neg Sg3) ("šoddâđ" Sg3) ; LIST HABEO-PL3 = ("leđe" Pl3) (V Neg Pl3) ("šoddâđ" Pl3) ; #!! !Pronoun sets # ------------ LIST MUN = (Pron Pers Sg1 Nom); LIST DON = (Pron Pers Sg2 Nom); LIST SON = ("sun" Pron Pers Sg3 Nom); LIST MOAI = (Pron Pers Du1 Nom); LIST DOAI = (Pron Pers Du2 Nom); LIST SOAI = (Pron Pers Du3 Nom); LIST MII-PERS = (Pron Pers Pl1 Nom); LIST DII = (Pron Pers Pl2 Nom); LIST SII = ("sun" Pron Pers Pl3 Nom); SET PPRON-NOM-NOT-DAT = MUN OR DON OR SON OR MOAI OR DOAI OR SOAI OR MII-PERS OR DII OR SII ; SET PPRON-DU-PL = MOAI OR DOAI OR SOAI OR MII-PERS OR DII OR SII ; SET PPRON-PL = MII-PERS OR DII OR SII ; SET PRON-DU = MOAI OR DOAI OR SOAI ; SET PPRON-NOT-SII = MUN OR DON OR SON OR MOAI OR DOAI OR SOAI OR MII-PERS OR DII ; LIST PPRON-GEN = (Sg1 Gen) (Sg2 Gen) (Sg3 Gen) (Du1 Gen) (Du2 Gen) (Du3 Gen) (Pl1 Gen) (Pl2 Gen) (Pl3 Gen); SET PPRON-NOT-GEN = (Pron Pers) - PPRON-GEN ; LIST SG-DEM = (Pron Dem Sg Nom); LIST PL-DEM = (Pron Dem Pl Nom); SET NOT-DEM = WORD - Dem ; LIST SG-PRON = (Pron Sg1) (Pron Sg2) (Pron Sg3) (Pron Sg) (Pron PxSg1) (Pron PxSg2) (Pron PxSg3); LIST DU-PRON = (Pron Du1) (Pron Du2) (Pron Du3) (Pron PxDu1) (Pron PxDu2) (Pron PxDu3); LIST PL-PRON = (Pron Pl1) (Pron Pl2) (Pron Pl3) (Pron Pl) (Pron PxPl1) (Pron PxPl2) (Pron PxPl3); LIST DU-PRON-NOTPX = (Pron Du1) (Pron Du2) (Pron Du3) ; LIST FIRST-PX = PxSg1 PxDu1 PxPl1 ; LIST DU-NR = Du1 Du2 Du3 ; SET NOT-SG-PRON = DU-PRON OR PL-PRON ; LIST DAT-PRON = ("dat") ("taat") ("tiet") ("tuot") ("tot") ; LIST QUANT-PRON = "ollu" "olu" "unnán" "váháš" "veaháš" "veháš" ; # This set is for choosing between Adv and Pron Indef. #!! !Adjectival sets and their complements # ------------------------------------- SET LEX-A = A - DER-A ; SET A-CASE = A - Attr - Adv ; LIST A-CC = A CC ; SET NOT-A = WORD - A ; # This is former NOT-ADJ SET NOT-A-COMMA = WORD - A - COMMA ; SET NOT-Attr = WORD - Attr ; SET NOT-A-PCLE = WORD - A - Pcle ; SET NOT-A-CC = WORD - A-CC ; # This set was removed, for a good reason? SET NOT-A-ADV = WORD - A - Adv OR ("maid") ; LIST NOMINAL-A = "guoktilaš" "lámis" "oasálaš" ("suddu" Der/laš) "viissis"; LIST OLLU = "ollu" "olu" ; # and many others #!! !Adverbial sets and their complements # ------------------------------------ SET LEX-ADV = Adv - (A*) ; SET NOT-ADV-DE = WORD - Adv ; SET NOT-ADV = NOT-ADV-DE OR ("de" Adv) OR CLB ; SET NOT-ADV-N = NOT-ADV - N; SET NOT-ADV-PCLE = NOT-ADV - Pcle ; SET NOT-ADV-INDEF = NOT-ADV - Indef ; SET NOT-ADV-PCLE-ILL-LOC-COM = WORD - Adv - Pcle - Ill - Loc - Com; SET NOT-A-ADV-PCLE = WORD - Pcle - A - Adv OR ("maid") ; # LIST MOVT = "govt" ("got" Adv) "mo" "mot" "mov" "movt" ; LIST MO-MANge = "danne" "goas" "gokko" "gos" "gosa" "govt" ("got" Adv) "makkár" "man" "manne" ("manin" Adv) "mo" "mot" "mov" "movt" ("nugo" @CVP) (V Qst); SET MO = MO-MANge - Foc/ge ; # Introduce finite clauses. LIST PLACE-ADV = "bajábealde" "davábealde" "lagabus" "máttabealde" "nuorttabealde" "oarjjábealde" "oarjjabealde" "olggobeale" "vuolábealde" ; # There will usually be a Gen in front. LIST DOPPE = "badjin" "bajil" "dakko" "dá" "dákko" "dáppe" "diekko" "dieppe" "do" "dokko" "doppe" ("duo" Adv) "duokko" "duoppe" "olgun" ; # Adverbs with a locativic form, but don´t get Loc as a tag. LIST DOHKO = "bajás" "deike" "diehke" "diehko" "dohko" "duohko" "lulás" "olggos" "ruoktot" "sisa" "vuovdimassii" ; # Adverbs with a illativic form, but they don´t get Ill as a tag. #!! !Sets for coordinators # ------------ SET Foc = Foc/ge OR Foc/gen OR Foc/ges OR Foc/gis OR Foc/naj OR Foc/ba OR Foc/be OR Foc/hal OR Foc/han OR Foc/bat OR Foc/son ; LIST NEGFOC = (Neg Foc/ge) ; LIST XGO = "dego" "dugo" "nugo" "seammaládjego" "seammaláhkáigo" ; # Compounds LIST SEAMMAX = "seamma_ládje" "seamma_láhkái" ; # Those combine with go LIST MADE = "mađe" "mađi" ; LIST DADE = "dađe" "dađi" ; SET CRD = COMMA OR CC OR NEGFOC OR XGO OR ("/") OR ("-") OR DADE ; # coordinators SET NOT-CRD = WORD - CRD ; SET LCRD = @CNP OR ("asdfasdf") ; # local coordinator SET GCRD = @CVP OR ("sadfasdf") ; # global coordinator SET CRD2 = (@CNP) OR COMMA OR NEGFOC OR XGO OR ("/") OR ("-") OR DADE ; # AFTER LCRD vs. GCRD disambiguation #!! !Sets for adverbs that have lookalikes # ------------------------------------- #!! Here come some adverbs that have identical twins in other POS. #!! If these are found in Adv contexts, we treat them as adverbs. LIST LACCAT-ADV = "absoluhtalaš" "agálaččat" "aitosaččat" "aktiivvalaš" "almmolaš" "analogalaš" "automáhtalaš" "álgoálgosaš" "álgovuolggalaš" "árbevirolaš" "beaivválaččat" "biologalaš" ("buhttenriekti" Der/laš) ("bustávva" Der/laš) "čálalaččat" "čearddalaš" "dábálaš" "duođalaččat" ("dutkanpolitihkka" Der/laš) "eahpedábálaš" "eahpeformálalaš" "eahpekritihkalaš" "eahpevirggálaš" "eaktodáhtolaččat" "ekologalaš" "ekologálaš" "ekonomálaš" "eksplisihtalaš" "elektrovnnalaš" ("eahpidit" VAbess) "etihkalaš" "etymologalaš" "fágalaš" "fonehtalaš" "fonologalaš" "fonotávttalaš" "formálalaš" ("fysiologa" Der/laš) "gaskamearálaš" "geavatlaš" "gelbbolaš" "geográfalaš" "gielalaš" ("girkoriekti" Der/laš) "globálalaččat" ("gorri" Der/laš) "govttolaš" "hálddahuslaš" "historjjálaš" "ideologalaš" "iešheanálaš" "implisihtalaččat" "jahkásaččat" "jeavddalaččat" ("jietnadatoahppa" Der/laš) "juridihkalaš" "konkrehtalaš" "kritihkalaš" "kronologalaš" "kulturhistorjjálaš" "kulturpolitihkalaš" "kultuvrralaš" "logihkalaš" ("luohtu" Der/laš) "máŋggafágalaš" "mekánalaš" ("metoda" Der/laš) "moralalaš" "morálalaš" "morfologalaš" "našuvnnalaš" "negatiivvalaš" "njálmmálaččat" "njuolgguslaččat" "oaiveáššálaš" "obbalaš" "obbalohkái" "oktasaččat" "oktilaš" "ollislaččat" "oppalaččat" "optimalalaččat" "ovttabealálaš" "ovttajienalaš" "ovttamielalaš" "pedagogalaš" "politihkalaš" "praktihkalaš" "prinsihpalaš" ("priváhtariekti" Der/laš) "profehtalaš" "psykologalaš" "ráfálaččat" ("reálapolitihkka" Der/laš) "riektehistorjjálaš" "rievttálaš" "riikkaidgaskasaš" "sámegielalaš" "riikkagottálaš" "ruđalaš" "rumašlaš" "sámepolitihkalaš" "sekundáralaččat" "semantihkalaš" "servodatávkkálaš" ("siviilariekti" Der/laš) "sosiálalaš" ("stáhtapolitihkka" Der/laš) "strategalaš" "teknihkalaš" "teorehtalaš" "topográfalaš" ("váldoášši" Der/laš) "virggálaš" "virolaš" ; LIST MOD-NP-ADV = "áibbas" "dušše" "erenoamážit" "goitge" "man" "measta" "meastui" "oalle" "oba" "oktiibuot" "oppa" "sullii" ; LIST MOD-ADV-ADV = ("áibbas" Adv) ("eanet" Adv) ("erenoamáš" Adv) ("erenoamáš" Adv) ("hirbmat" Adv) "hui" "man" ("mealgat" Adv) "menddo" "oalle" "nu" "oba" "oppa" ; LIST EASKKA = "easkka" "easka" ; LIST NOT-ARG-ADV = "aiddo" "ain" "aivve" "albma" "aŋkke" "álggos" "báifáhkka" "beanta" "beare" ; #LIST NOT-ARG-ADV2 = "aiddo" "ain" "aivve" "albma" "aŋkke" "álggos" "álgobáliid" "álo" "báifáhkka" "beanta" "beare" "dakkaviđe" "dal" "dan_dihte" "danne" "dasto" "dattetge" ("dábálaš" Adv) "dávjá" "de" "dieđinge" "dieđusge" "duođaid" "easkka" "fal" "fargga" "fas" "fárrolaga" "gal" "goas" "goasse" "gos" "gosa" "gostege" "govt" "gusto" "hedi" "juo" "justa" "loahpas" "maiddái" "manin" "manne" "nuppes" "suige" "šat" "vel" "viimmat" "vuos" ; LIST ADV-NOT-V = "dušše" "viimmat" ; LIST ADV-NOT-N = "easka" "várra" ; LIST ADV-NOT-PROP = "Ain" "Anne" "Diego" "Dieppe" "Enge" "Galle" "Haga" "Joba" "Johan" "Liikka" "Mai" "Mannes" "Mo" "Naba" "Nan" "Oktan" "Sierra" "Sokka" "Villa" ; SET ADV-NOT-OTHER-POS = ADV-NOT-V OR ADV-NOT-N OR ADV-NOT-PROP ; LIST MANNEL = "maŋŋel" "maŋŋil" "maŋŋá" ; #!! !Sets of elements with common syntactic behaviour # ================================================ SETS #!! !Sets for verbs # ----- LIST NOT-REAL-V = (Actio Nom) (Actio Gen) (Actio Loc) (Actio Com) PrsPrc ; SET REAL-V = V - NOT-REAL-V ; #!! V is all readings with a V tag in them, REAL-V should #!! be the ones without an N tag following the V. #!! The REAL-V set thus awaits a fix to the preprocess V ... N bug. SET LEX-V = V - DER-V ; # VERB but not DER-V # The set REAL is smaller than COPULAS, made for verbs with PrfPrc complements: Seammás REAL-COPULAS son dovdan iežas... LIST REAL-COPULAS = "täiđiđ" "leđe" "soaitit" "vaijeeđ" ; #!! * The set COPULAS is for predicative constructions LIST COPULAS = "täiđiđ" "karttâđ" "leđe" "soaitit" "šoddâđ" "orroođ" "vaijeeđ" ; # "bissut" ? # 'Dáidit' can appear without 'leat'. SET NOT-COP-V = V - COPULAS ; LIST MOD-ASP = "áiguđ" "bállet" "berret" "täiđiđ" "ferttiđ" "kolgâđ" "gillet" "lávet" "sättiđ" "seahtit" "soaitit" "viggat" ; # Verbs that never have arguments of their own - so we leave out "áiguđ", for ex. LIST AUX-OR-MAIN = "áiguđ" "älgiđ" "peessâđ" "kolgâđ" "halijdiđ" "mättiđ" "nagadit" "nagodit" "ollit" "orroođ" "sihtat" "vaijeeđ"; # These verbs can take arguments, so they do not belong in the AUX group, # but they are nevertheless mapped to (@+FAUXV). # Added "älgiđ" to the group (Lene) - Made rules for "pyehtiđ" which sometimes can be AUX # Magga (1982: 120): áigut, dáidit, deaivat, fertet, galgat, lávet, máhttit, oažžut, sáhttit, soaitit, veadjit - in some of the meanings # Halvhjelpeverb: álgit, berret, dohkket, gártat, heivet, liigut, šaddat - in some of the meanings SET AUX = COPULAS OR Neg OR MOD-ASP OR AUX-OR-MAIN ; SET NOT-AUX-V = V - AUX ; # This is former V-NOT-AUX # The set of verbs that cannot be auxiliaries. # Does not include AUX-OR-MAIN. SET VFIN-NOT-AUX = VFIN - AUX ; SET MAIN-V = V - COPULAS - Neg - MOD-ASP OR ("orroođ") ; # All active verbs with a TV tag, including AUX-OR-MAIN. LIST V-TRANS = (V TV) (IV Der/ahtti) (IV Der/h) ; SET TRANS-ACT-NOT-AUX-V = V-TRANS - Der/Pass - AUX ; #!! TRANS-V is the set for verbs really taking objects SET TRANS-V = V-TRANS - Der/Pass + REAL-V ; #SET TRANS-V = V-TRANS - Der/Pass - (Actio Nom) - (Actio Gen) - (Actio Loc) - (Actio Com) - PrsPrc ; #!! * Sets for verbs choosing oblique objects or adverbials # - - - - - - - - - - - - - - - - - - - - - - - - - - - # bargat "čoallut" "borrat" lohkat "gazzat" vuoššat #!! * __STVLIST__ is the list of strictly transitive verbs. In the rules, refer not to STVLIST, but to the set STV defined below. LIST STVLIST = (IV Der/ahtti) (IV Der/h) "addit" "amašit" "ásahit" "atnit" "ánssášit" "árvalit" "árvidit" "árvvoštallat" "ásahit" "ávžžuhit" "bajidit" "bassat" "bearrat" "biebmat" "bidjat" "bilidit" "billistit" "bissehit" "bisuhit" "boaldit" "boktit" "borahit" "buhtadit" "buktit" "buoridit" "caggat" "coggalit" "cealkit" "cegget" "čađahit" "čatnat" "čielggadit" "čilget" "čoaggit" "čoavdit" "čohkket" "čuoččuhit" "čuohppat" "čuollat" "čuovvulit" "dadjat" "dagahit" "dahkat" "dáhkidit" "dáhttut" "dárbbahit" "dárbbašit" "dárkkistit" "dávistit" "deaivat" "deattuhit" "deavdit" "diehtit" "dikšut" "diktit" "doahttalit" "doaimmahit" "doalahit" "doallat" "doalvut" "doarjut" "dohkkehit" "dovdat" "dovddahit" "duođaštit" "eahpidit" "eaiggáduššat" "eaktudit" "ealáskahttit" "ealihit" "eavttuhit" "evttohit" "fállat" "fidnet" "fievrridit" "fuobmát" "fuolahit" "fuomášit" "garvit" "gaskkustit" "gádjut" "gáhttet" "gáibidit" "gáržžidit" "gávdnat" ("gávnnadit" Sg1) ("gávnnadit" Sg2) ("gávnnadit" Sg3) "geahčadit" "geahččat" "geassit" "geatnegahttit" "geavahit" "gieđahallat" "giddet" "goddit" "gohččut" "gohčodit" "goikadit" "gokčat" "goldit" "gozihit" "guoddalit" "guoddit" "guođđit" "guođohit" "guorahallat" "guorrat" "guoskkahit" "hábmet" "háhkat" "hálddašit" "heaittihit" "heivehit" "hilgut" "ipmirdit" "iskat" "iskkadit" "jeahkit" "jođihit" "juksat" "juohkit" "juolludit" "kártet" "lágidit" "láhčit" "láigohit" "loahpahit" "lohpidit" "loktet" "luoikat" "luoikkahit" "luoitit" "massit" "mearkkašit" "mielddisbuktit" "movttiidahttit" "muddet" "muitalit" "muitit" "muittuhit" "namahit" "nammadit" "namuhit" "nannet" "nanosmahttit" "njiellat" "nuppástuhttit" "oaidnit" "oastit" "oaivvildit" "oamastit" "oažžut" "ođasmahttit" "ođastit" "ollašuhttit" "organiseret" "ovdanbuktit" "ovdánahttit" "ovddastit" "ovddidit" "prioriteret" "ráddjet" "ráđđet" "ráfáidahttit" "ráfáiduhttit" "ráhkadit" "rávkat" "rávvet" "rievdadit" "rihkkut" "sakŋadit" "sáddet" "sáhtostit" "sávvat" "seaguhit" "seailluhit" "sihkkarastit" "sihtat" "siskkildit" "sisttisdoallat" "suodjalit" "suovvat" "unnidit" "vađastit" "vahágahttit" "váillahit" "váldit" "válljet" "várret" "vásihit" "váttásmahttit" "viiddidit" "vuhtiiváldit" "vuođđudit" "vuođđudallat" "vuohttit" "vuoitit" "vuojuhit" "vuoruhit" "vuostáiváldit" "vuosttaldit" "vuovdit" ; # Strictly transitiv-verbs - a start. This set is ment as a help choosing Acc or Gen. Example: "Mun borren eatni kafeás." - there is Gen, no Acc, even if the verb is transitive. That´s why "borrat" is not in this set. # These verbs: "addit", "fidnet" and "oažžut" can, when it´s about sex, be without object: "Son oaččui gonagasa bártnis." SET STRICT-TV-V = STVLIST + V - Der/Pass ; #!! STRICT-TRANS-V is the set for verbs which don't let a GenAcc be a modifier of anything else than an object, e.g. Mun organiseren eatni gievkkanis. - eatni wants to be the object SET STRICT-TRANS-V = STRICT-TV-V + REAL-V ; LIST LOC-V = "ávkkástallat" "ballat" "peessâđ" "beroštit" "biehttalit" "bihtit" "ceavzit" "dinet" "dolkat" "eastadallat" "eastadit" "fitnat" "fuolahit" "fuollat" "garvit" "gažadit" "heaitit" "hehttet" "ilbmat" "jearrat" "jearralit" "luohpat" "máinnašit" "nohkkot" "oassádallat" "oassálastit" "spiehkastit" "váibat" "váruhit" "vástidit" ; #Note that "fuolahit" obviously has two homonymous variants: #fuolahit1+Acc, fuolahit2+Loc LIST COM-V = "álggahit" "älgiđ" "árvalit" "árvvohuššat" "ávkašuvvat" "bálddastahttit" "bálddalastit" "bártašuvvat" "birgehallat" "birget" "bivvat" "buohtastahttit" "čoahkkinastit" "deaivvadit" "deavdit" "digaštallat" "doarrut" "duhkoraddat" "ealihit" "flirtet" "gávnnadit" "gárvodit" "giksašuvvat" "gilvalit" "gulahallat" "gulaskuddat" "hilbošit" "joatkit" "juogadit" "juohkit" "láhttet" "leaikkastallat" "lohpádaddat" "lohpádallat" "lonuhit" "meannudit" "malssidit" "molssodit" "náitalit" "oktiibidjat" "oahpásmuvvat" "ovttasbargat" "ovttastahttit" "rahčat" "reivvestaddat" "riidalit" "riiddáskit" "rohcošit" "ságastit" "seaguhit" "servvoštallat" "servvoštaddat" "soabadit" "soahpat" "soahtat" "soardit" "stálostallat" "stoahkat" "šiehtadallat" "šiehtadit" "šiehttat" "veahkehit" "veardidit" "viiddidit" "vrd" ; #Note that "leaikkastallat" has two homonymous variants: #leaikkastallat1 (IV), leaikkastallat2+Com LIST ILL-V = "áibbašit" "älgiđ" "ásaiduvvat" "báitit" "bahkket" "peessâđ" "čohkkedit" "čujuhit" "čuohcit" "deaivat" "doaškut" "dorvvastit" "došket" "duhtat" "gullat" "guoskat" "gustot" "hárjánit" "heivet" "irgidit" "irggástallat" "jáhkkit" "liikot" "luohttit" "mannat" "máhccat" "mieđihit" "miehtat" "njiedjat" "oahpásmuvvat" "oahpásnuvvat" "ollet" "oskut" "riepmat" "ráhkkanit" "soahpat" "searvat" "suhttat" "váikkuhit" "vástidit" "vuolgit" ; ###"geahččat" Lene: fjerna denne LIST TRANSL-V = "jápmit" "duššat" "hávkat" "náitalit" "gaskkalduvvat" "nohkat" "goarránit" "heahpanit" "boakčánit" "šlundut" "ráigánit" "vuollánit" "gopmánit" "fuotnánit" "roahppánit" "reakčanit" "bieđganit" "luoddanit" "guvggodit" "liegganit" "suorganit" "báhkkanit" "cuovkanit" "hedjonit" "lohppet" "goikat" "galbmot" "goallut" "ruostut" "buoidut" "guvggodit" "suvrut" "suddat" ; # Taken from Helander (2001) p. 89, might be useful in the future as those verbs typically take humans and places in illative case. LIST REKS-V = "áibbašit" "deaivat" "dorvvastit" "duhtat" "gustot" "hárjánit" "jáhkkit" "liikot" "mieđihit" "ollet" "ráhkkanit" "soahpat" "searvat" "vuolgit" "beroštit" "biehttalit" "bihtit" "ceavzit" "dinet" "dolkat" "eastadallat" "eastadit" "fuolahit" "fuollat" "geargat" "heaitit" "luohpat" "oassálastit" "váikkuhit" "váruhit" ; # This set is for giving infitives @ADVL after the verb. LIST ACC-LOC-V = "biehttalit" "čuovvut" "earuhit" "gieldit" "jearrat" ; LIST ACC-ILL-V = "addit" "bidjat" "mearkkašit"; # Two-place predicates that take a direct object and an illative adverbial. LIST MIELDE-V = "addit" "bidjat" "täiđiđ" "leđe" "oastit" "oažžut" "váldit" ; # Verbs that take mielde as their complement. # Son attii girjji mielde. LIST TIME-ADVL-V = "ádjánit" "ássat" "bargat" "bistit" "bivdit" "eallit" "fievrridit" "guohtut" "joatkit" "láddet" "oahpahit" "ođasmahttit" ; # Do not take members of the time set as an object LIST TIMEOBJECT-V = "addit" "atnit" "árvalit" "bálvalit" "čuovvut" "deavdit" "diŋgot" "evttohit" "fátmmastit" "gáibidit" "gávdnat" "geavahit" "gierdat" "guhkidit" "hábmet" "jorgalit" "juolludit" "lasihit" "liigudit" "loahpahit" "loaktit" "markeret" "mearridit" "molsut" "oanidit" "oažžut" "soahpat" "šiehttat" "várret" "viiddidit" ; # might take time as an object - verbs which are not members of PLACE-V: LIST DURATION-V = "ádjánit" "bargat" "bistit" "čuoigat" "eallit" "gollat" "guohtut" "leđe" "vázzit"; LIST POINT-IN-TIME-V = "árrit" "bissehit" "caggat" "cakkadit" "cakkastallat" "doalahit" "doallat" "duostut" "dustet" "eastadit" "gieldit" "goahcat" "heađuštit" "hehttet" ; LIST ROUTE-ADVL-V = "pyehtiđ" "čuoigat" ; # bevegelse langsmed noe, innafor et bestemt område LIST ROUTEOBJECT-V = "ásahit" "bidjat" "botnjat" "basuhit" "buoridit" "čielggadit" "čuovvulit" "čilget" "čuorvut" "čurvet" "dieđihit" "duođaštit" "duorggastit" "geavahit" "geahpedit" "geahpidit" "gudnejahttit" "guorahallat" "gieđahallat" "guođđit" "gilljut" "heahtit" "huikit" "huikkádit" "juoigat" "lávlut" "lohkat" "loahpahit" "mearridit" "máidnut" "nannet" "njulget" "oahpahit" "ráhkadit" "sivdnidit" "suokkardit" "unnidit" "válmmaštit" "vurket" ; LIST HAB-V = "pyehtiđ" "leđe" "goallut" "heaŋgát" "jápmit" "šoddâđ" ; # To be used in habitative-sentences. #!! !Valency sets # - - - - - - - LIST INF-V = "astat" "ádjánit" "áiguđ" "älgiđ" "ásahit" "bágget" "bávččagit" "peessâđ" "berret" "bivdit" "bivvat" "bistit" "pyehtiđ" "bovdet" "čohkkát" "čohkkedit" "čohkánit" "čuoččahit" "čuoččastit" "čuorvut" "čurggodit" ("dadjat" Der/PassL) ("dadjat" Der/PassS) "dagahit" "dáhttut" "täiđiđ" "dárbbašit" "defineret" "diktit" "doaivut" "doapmat" "duostat" "ferttiđ" "fuobmát" "fuolahit" "kolgâđ" "gáibidit" "gárrut" "karttâđ" "geahččalit" "geargat" "geatnegahttit" "gierdat" "gillet" "gohččut" "háhppehit" "halijdiđ" "hárjánit" "heivet" "lávet" "liikot" "lihkkat" "mannat" "mättiđ" "máššat" "movttiidahttit" "muitit" "nagodit" "navdit" "oahpahit" "oahpástuvvat" "oahppat" "oažžut" "ollet" "ribahit" "riepmat" "sättiđ" "seahtit" "sihtat" "soaitit" "suovvat" "šoddâđ" "stađđat" "vaijeeđ" "viggat" "viššat" "vuogáiduvvat" "vuolgit" "vuollánit" "vuordit"; LIST ACC-INF-V = "bivdit" "čuorvut" "dagahit" "diktit" "gohččut" "movttiidahttit" "sihtat" "suovvat" ; # These are verbs taking accusative objects and infinitives at the same time; # a subset of INF-V. #$ Ii suova nieiddas náitalit. LIST OPRED-V = "alidit" "atnit" "álggahit" "ásahit" "bargat" "bidjat" "ceavzit" "dadjat" "dahkaluddat" "dahkat" "doalahit" "dovdat" "dulkot" "karttâđ" "geavahit" "geahččat" "gohčodit" "gohččut" "kvalifiseret" "málet" "meroštallat" "meroštallojuvvot" "navdit" "oaidnit" "oaivvildit" "sihkkarastit" "váldit" "válljet" "rábmot" "vihahit" ; # Verbs that occur with objects that have secondary predicates. LIST OKTII-V = ("boallu" Der/huvva) "goallostit" "beaškkehit" "bidjat" "čatnat" "suddat" "heivet" "bidjat" "časkit" "geassit" "gullat" "rehkenastit" "ordnet" "soahpat" "gávnnadit" "heivehit" "doaibmat" "iskat" "laktit" "seaguhit" "sorrot" ; # Danger: This list could be too long, in certain respects. # TODO: Think of counter examples, i.e. sentences where we have these verbs, but where oktii is not an adverbial. LIST VGEN-V-TRIGGER = "peessâđ" "bidjat" "bijadit" "bivdit" "pyehtiđ" "buktit" "čohkket" "čuovvut" "doalvut" "duolmmadit" "fidnet" "fitnat" "kolgâđ" "girdit" "gálašit" "gávdnat" "goastit" "guođuhit" "gurgalit" "gárgidit" "jávkkihit" "joatkit" "johtit" "jorgut" "loahpahit" "mannat" "mátkkoštit" "njahkalit" "njoammut" "oasálastit" "rasttildit" "ruohttat" "sihkkelastit" "váccašit" "vájuldit" "vánddardit" "viehkat" "viehkalit" "viežžat" "vuodjit" "vuolgit" ; LIST VGEN-V = "bassit" "bárdnat" "bealkit" "biškut" "pyehtiđ" "borrat" "civkit" "čárvut" "čállit" "čeargut" "čierrut" "čuoigat" "čuorvut" "doarggistit" "duorrat" "fáiput" "garrudit" "gállit" "ohcat" "geargat" "geavzut" "gievvut" "gilljut" "girdit" "gullat" "guoddit" "heahpanaddat" "hoigat" "holvut" "huikit" "hupmat" "jápmit" "johtit" "jorgut" "juoigat" "láddjet" "lávlut" "luoibmat" "murdit" "njáhkat" "njoammut" "njurgut" "oađđit" "oahkut" "oaidnit" "orroođ" "reaškit" "riidet" "rohkut" "ruohttat" "ruossut" "sáđđat" "sihkkelastit" "skeaikit" "skierbmut" "soabbut" "speažžut" "suhkat" "suoibut" "šlivgut" "šloahtat" "šnjirgut" "vázzit" "viehkat" "vuodjat" "vuodjit" "vuohčut" "vuoitit" "vuoššat" ; LIST SOURCE-V = "gáibidit" ; LIST MOVEMENT-V = "ádjit" "peessâđ" "pyehtiđ" "čuoigat" "čuoiggadit" "fárret" "finadit" "finihit" "fitnat" "gálašit" "gállit" "girdit" "johttát" "johtit" "jorahallat" "mannat" "mátkkoštit" "njoammut" "njuiket" "ollit" "riidet" "ruohttat" "sáhtostit" "sihkkelastit" "soabbulit" "soabbut" "šloahtat" "váccašit" "vádjolit" "vájaldit" "vájuldit" "vánddardit" "vázzit" "viehkalit" "viehkat" "viežžat" "vuodjalit" "vuodjat" "vuodjit" "vuojadit" "vuojašit" "vuolgit" ; # These verbs typically combine with place adverbials in the genitive case @ADVL # (i.e. not accusative) I am not sure if the verbs in the second line do that too. They denote movement anyway. # These verbs take GEOGRAPHICAL-PLACE in Acc @OBJ. LIST JOHTIT = "čuoigat" "čuoiggadit" "gálašit" "gállit" "girdit" "johttát" "johtit" "mátkkoštit" "njoammut" "riidet" "ruohttat" "sihkkelastit" "soabbulit" "soabbut" "šloahtat" "váccašit" "vádjolit" "vájaldit" "vájuldit" "vánddardit" "vázzit" "viehkalit" "viehkat" "vuodjalit" "vuodjat" "vuodjit" "vuojadit" "vuojašit" ; LIST HUMAN-ACTIVITY-V = "áitit" "bassit" "báhčit" "bealuštit" "beaskidit" "beastit" "bidjat" "biepmat" "bivdit" "boaldit" "botket" "buktit" "buvttadit" "časkit" "čatnat" "čájehit" "čállit" "čoaggit" "čoavdit" "čugget" "čuohppat" "dearpalit" "dearpat" "dearvvahit" "deavdit" "devdnet" "dikšut" "divvut" "doarrádallat" "doidit" "dolastit" "čuojahit" "dovddastit" "dubmet" "duddjot" "duvdilit" "ferdnet" "gáhkket" "gárvodit" "gásttašit" "gávkat" "geahččat" "gilvit" "goarrut" "goddit" "gođđit" "gohččut" "goikadit" "goivet" "gokčat" "gottihit" "guldalit" "guolástit" "hábmet" "hervet" "hoigat" "hoitát" "hukset" "huškut" "huškkohallat" "jugahit" "juhkat" "juksat" "juogadit" "juohkit" "láddjet" "láibut" "láktadit" "loaiddastit" "luddet" "merket" "mihtidit" "murret" "nannet" "náitalit" "njuoskadit" "oahpahit" "oastit" "ohcat" "olahit" "rahpat" "ráhkadit" "ráidnet" "rátkit" "registreret" "rekruteret" "riŋget" "ruohkkat" "sahát" "sáddet" "sáltet" "sárgut" "sihkkut" "siktet" "skihtardit" "skoalkalit" "tevdnet" "vadjat" "veahkehit" "vikšet" "vuođđudit" "vuosehit" "vuoidat" "vuoiddadit" "vuoitit" "vuostáiváldit" "vuoššat" "vuovdit" "vurket" ; # in contrast to abstract "activities" and static verbs. # According to the rules choosing Loc or Com, all activity-verbs do not select TOOL, ABSTR-TOOL, CONCEPT or HUMAN in (Pl Loc). LIST BODY-ACTIVITY-V = "borrat" "čiekčat" "čujuhit" "čuorbmat" "gullat" "guoskkahit" "jorahit" "lihkahit" "lihkastahttit" "loktet" "njávkkadit" "njávkkastit" "oaidnit" "seavvit" ; # These verbs can also have BODY as a tool. The verb-set belongs to the superset of dynamic-verbs, so they will also work with TOOL and ABSTR-TOOL in Com. "Giehta" is in both the TOOL-set and the BODY-set because it selects in Com to a lot of verbs. LIST PLACING-ACTIVITY-V = "bidjat" "buonjostit" ; LIST WRITING-ACTIVITY-V = "čállit" ; LIST HANDICRAFT-ACTIVITY-V = "buddet" "botnit" "goarrut" "hervet" "vadjat" "vikšet" ; SET ACTIVITY-V = BODY-ACTIVITY-V OR WRITING-ACTIVITY-V OR PLACING-ACTIVITY-V OR HUMAN-ACTIVITY-V OR HANDICRAFT-ACTIVITY-V ; LIST DADJAT = "čuoččuhit" "dadjat" "lohkat" "muitalit" ; # This set is for cealkkavástta: DADJAT + Acc + Inf or PrfPrc LIST HUPMAT = "dáikit" "dárostit" "digáštallat" "digaštit" "duoldat" "háladit" "háleštit" "hállat" "hoallat" "humadit" "hupmat" "logaldallat" "máidnut" "máinnašit" "muitaladdat" "njurgut" "oaivvildit" "savkalit" "ságastaddat" "ságastallat" "ságastit" "sámástit" "sámistit" "sárdnidit" "sárdnut" "sártnodit" "solžat" "suomastit" ; # These should not take HUMAN as object LIST VERBAL-ACTIVITY = "árvalit" "cealkit" "čilget" "čuoččuhit" "basuhit" "bealkit" "cuoigut" "čuorvut" "čurvet" "dadjat" "gielistit" "gilljut" "gopmulit" "háladit" "háleštit" "hállat" "hoallat" "huikit" "huikkádit" "jearrat" "juoigat" "kommenteret" "lávlut" "lohkat" "muitalit" "namahit" "namuhit" "rávvet" "sivdnidit" "váruhit" "vástidit" ; SET VERBAL-ACTIVITY-V = VERBAL-ACTIVITY OR HUPMAT ; #Under construction! (as most of the other LISTs) # According to the rules choosing Loc or Com, the these verbs select TOOL, ABSTR-TOOL, CONCEPT or HUMAN in (Pl Loc). # SATNI in Com LIST HUMAN-AGENT-V = "áŋgiruššat" "ásahit" "beahttit" "buoridit" "čielggadit" "čuovvulit" "dássidit" "deattastit" "deattuhit" "dieđihit" "dievvat" "duođaštit" "geahpedit" "geahpidit" "gudnejahttit" "guorahallat" "illudit" "lassánit" "liekkadallat" "loahpahit" "luohpat" "mearridit" "moivašuhttit" "namuhit" "nannet" "oassálastit" "suokkardit" "unnidit" "váikkuhit" "válmmaštit" "verrošit" "vurket" ; # According to the rules choosing Loc or Com, the these verbs do not select TOOL, ABSTR-TOOL, CONCEPT, SATNI or HUMAN in (Pl Loc). LIST NOT-HUMAN-OBJECT-V = "bargat" "borrat" "čállit" "lohkat" "vuodjit" ; # transitive verbs that typically do not have humans as their object and usually have an intransitive reading LIST USUALLY-IV = "boradit" ; # TV verbs which usually are used intransitively #LIST ABSTR-EVENT-V = "lassánit" ; # In contrast to the HUMAN-AGENT-V set, this one presupposes no human or human-like actor who initiates the action. LIST INTELLECTUAL-ACTIVITY-V = "dovdat" "fuobmát" "fuomášit" "huobmát" "jurddahit" "jurddašit" "smiehttat" ; # According to the rules choosing Loc or Com, the these verbs do not select TOOL, ABSTR-TOOL, CONCEPT or HUMAN in (Pl Loc). LIST VEHICLE-PLACE-V = "addit" "bearrat" "gaikkihit" "gáibidit" "geiget" "oastit" "oažžut" "suoládit" "váldit" ; # According to the rules choosing Loc or Com, these verbs do not select TOOL, ABSTR-TOOL and CONCEPT in (Pl Loc), but HUMAN or ACTOR in (Pl Loc). # HUMAN is source and locative, VEHICLE is locative LIST VEHICLE-TOOL-V = "peessâđ" "pyehtiđ" "buktit" "doalvut" "fievrridit" "vuolggahit" ; # HUMAN is source and locative, VEHICLE is comitative SET HUMAN-SOURCE-VEHICLE-V = VEHICLE-PLACE-V OR VEHICLE-TOOL-V ; # The two subsets differ in their choice of case for members of VEHICLE, but both choose locative for members of the set HUMAN (with the thematic role source) LIST ABSTR-ENTITY-COM-V = "investeret" "lihkosmuvvat" "lihkosnuvvat" "lihkostuvvat" "lihkustuvvat" "ruhtadit"; # According to the rules choosing Loc or Com, these verbs do not select TOOL, ABSTR-TOOL, CONCEPT, ABSTR-ENTITY and ACTOR in (Pl Loc). LIST ONLY-PLACE-LOC-V = "álggahit" "bártidit" "bargat" "čohkkedit" "dahkat" "geahččalit" "olahit" "veahkehit" ; # According to the rules choosing Loc or Com, these verbs only select (Pl Loc) if PLACE or ORGANIZATION. LIST HUMAN-LOC-V = "atnit" "báhcit" "geavahit" "gohčodit" "namuhit" ; # According to the rules choosing Loc or Com, these verbs choose only (Sg Com) if CONCEPT or HUMAN or "sátni". # Abstract #!! * __PLACE-V__ Those get only not locative if the target is a member TOOL, ABSTR-TOOL or ANIMATE or CONCEPT. Selects more locatives than ONLY-PLACE-LOC-V LIST PLACE-V = "ássat" "buolvvastallat" "buolvvastit" "čippostallat" "čohkkát" "čohkahit" "čuožžut" "čuččodit" "morihit" "gullát" "morránit" "orroođ" "orodit" "stuorrut" "veallát" "veallahit" ; LIST ABSTR-PLACE-V = "váilut" "heivet" "hiehpat" "sisttisdoallat" "soahpat" "šiehtat"; # Verbs without agent # TIME/AIGODAT are locative LIST STATE-V = "eallit" ; LIST REM-WITH-PARTS = "gaikkihit" ; # Belongs to the DYNAMIC-V. They also take PARTS in comitative case. LIST PERCEPTION-V = "áicat" "dovdat" "ealvit" "fuomášit" "fuobmát" "gullat" "haksit" "huobmát" "huomihit" "oaidnit" ; LIST ILLNESS-V = "buohcat" "buohccát" ; # "dearvvašmahttit" "dearvvašmuvvat" "dearvvašnuvvat" "dearvvaštuvvat" ; LIST ADV-PX-V = "geahččat" ; ## son geahččá birrasis # HIERARCHY: #SET STATIC-V = PLACE-V OR EMOTION-V OR PERCEPTION-V ; SET DYNAMIC-V = ACTIVITY-V OR MOVEMENT-V OR VERBAL-ACTIVITY-V OR HUMAN-AGENT-V OR INTELLECTUAL-ACTIVITY-V OR ABSTR-ENTITY-COM-V OR HUMAN-SOURCE-VEHICLE-V OR REM-WITH-PARTS ; # According to the rules choosing Loc or Com, dynamic-verbs do not select TOOL, ABSTR-TOOL or CONCEPT in (Pl Loc). # Human becomes either Loc or Com depending on its subset membership. SET N-TIMEOBJECT-V = MOVEMENT-V OR ACTIVITY-V OR VERBAL-ACTIVITY-V OR INTELLECTUAL-ACTIVITY-V OR PLACE-V ; # Those verb sets in addition to TIMEADVERBIAL-V do not take TIME expressions as objects LIST MUITALIT = "árvalit" "bivdit" "boagustit" "cealkit" "cuoigut" "čilget" "čurvet" "čuorvut" "dadjat" "dahkaluddat" "deattuhit" "doaivut" "eahpidit" "geardduhit" "geažuhit" "gielistit" "gilljut" "hállat" "hoallat" "huikit" "huikkádit" "imaštallat" "jearrat" "jievžat" "juoigat" "jurdilit" "jurddašit" "kommenteret" "lávlut" "lasihit" "loahpahit" "lohkat" "lohpidit" "máidnut" "máinnašit" "muitalit" "muittuhit" "nágget" "njávggádit" "oaivvildit" "rávvet" "savkalit" "sárdnidit" "šuohkihit" "váidalit" "váruhit" "vástidit" ; #$ Deaŧalaš lea sihkkarastit eamiálbmogiid ovddastusa dákkár čállingottis, dadjá Keskitalo. #!! !Adverb sets # ------- # Adverbs as predicates # - - - - - - - - - - - # in combination with verbs LIST COM-ADV = "fárrolaga" "oktan" "oktanaga" "ovttamielas" "ovttas" "ovttasráđiid" "searválagaid" "searválaga" ; # Could also be perceived as particles within complexs verbs. # others: vuhti combines with váldit - Com # Other adverb sets # - - - - - - - - - LIST GRADE-ADV = "áibbas" "beare" ("duođaid" Adv) ("eanet" Adv) "erenoamán" "erenoamáš" "hirbmat" "hui" "ila" "issoras" ("man" Adv) ("mealgat" Adv) ("mearkkašahtti" Adv) "measta" "menddo" "muhtun_muddui" "nu" "oalle" "oba" ("oppa" Adv) "sakka" ("seammá" Adv) ("veaháš" Adv) ("uhccán" Adv) ("unnán" Adv) "vehá" "veháš" "veahá" "veaháš" "viehka" ; LIST PLURALIZER = "buot" "buotlágan" "buotlágaš" "earálágan" "iežálágan" "gait" "gaitlágan" "goappeš" "goappašat" "máŋggalágan" "moattelágan" ; # Singular nouns can have a plural form combined with those LIST BUOT = "buot" "gait" "gaitin" "gaitdivnnat" ; #!! !Adjective sets # ---------- # Lexical valency sets # - - - - - - - - - - - # here we have adjectives according to their semantic properties LIST NUMAG-A = "čeahppi" "viššal" "láiki" ; # This set for vuovdi etc., not for nisson etc. # Here thus not ?stuorra vuovdi, etc, # in periphrastic constructions (together with "leđe") # these subcategorize for comitative, locative etc. depending on # the noun's semantic properties LIST COM-A = "duhtameahttun" "duđavaš" "duhtavaš" "ollis" "oppa" ; LIST ILL-A = "gullevaš" "bahá"; ## Ja danin son lei šaddan nu bahá tálaide ja bustávaide. LIST ACTIVITY-A = "hilbat" "oskkáldas" ; # denote som kind of activity, might take HUMAN comitative? LIST DEHALAS = "dábálaš" "dehálaš" "deaŧalaš" "mearkkašahtti" "eahpedábálaš" "vejolaš" "suohtas" ; # When Attr = pred.form #$ Lea suohtas kurssas. # not Attr #$ Lea čuovvovaš kurssas. # Attr # Nickel: predicative adjectives (take a complement) "fargat" "heavnnas" "sáiggas" "suhtas" # Other adjective sets # - - - - - - - - - - - LIST A-N = "buoidi" "čeahppi" "headju" "heittot" "jalla" "neavri" "nuorra" "oahpis" "oarbbis" "ráhkis" "rikkis" "váivváš" "vuoras"; # nouns that have very specific semantics and are derived from adjectives # those nouns are animate LIST A-N-CASE = "varas" ; # adjectives which are also nouns in other cases than nominative LIST NON-GRADE-A = "sápmelaš" "alternatiiva" ; # gradable under certain circumstances, for example if we write "nu" "hirbmat" "hui" "oalle" "oppa" "veháš" # mon dagahallan NU sápmelažžan = jeg later som jeg er SÅÅ same/samisk? # mon anán du VIEHKA sápmelažžan LIST GRADE-A = "fávru" "headju"; # The ones that have a strong adjective meaning, and are inclined to be adjectives rather than nouns in Ess constructions LIST A-LEX-AS-NOUN = "bassi" "guovddáš" "nuorra" "oahpis" "váivi" "oainnus"; # Those are quite strongly lexicalized as nouns. NBNB Earlier LEX-A, but this was another set LIST TIME-A = "boahtte" "čuovvovaš" "maŋemus" "maŋimus" "ovddit" ("mannat" PrfPrc) ("vássit" PrfPrc) ; LIST DURATION-A = "heila" "eanas" "eanet" "geažo" "geažos" "guhkki" "obba" "oba" "ollis" "oppa" "visot" ; LIST POINT-IN-TIME-SPEC = "dološ" "eará" "iežá" "nubbi" ; #!! !NP sets defined according to their morphosyntactic features # - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - SET NORM-LOC = Loc - (South Loc) ; LIST N-SG-NOM = (N Sg Nom); SET LEX-N = N - DER-N ; LIST PROP = (N Prop); SET COMMON-N = N - Prop; SET HEAD-N = N - RCmpnd ; SET HEAD-N-NOM = (N Nom) - RCmpnd ; SET SUBJECTHEAD = N OR A OR Pron - Refl ; # These, can be subject heads SET NP = N OR A ; # anything that can take except numerals SET NP-HEAD = Pron OR HEAD-N - ("buorre") ; SET NP-HEAD-SG = SG-PRON OR (N Sg) OR (A Sg) - RCmpnd - Dem - ("buorre"); SET NP-HEAD-PL = PL-PRON OR (N Pl) OR (A Pl) - RCmpnd - Dem - ("buorre"); SET NP-HEAD-SG-NOM = SG-PRON + Nom OR (N Sg Nom) OR (A Sg Nom) - ("buorre") - RCmpnd ; SET NP-HEAD-PL-NOM = PL-PRON + Nom OR (N Pl Nom) OR (A Pl Nom) - RCmpnd - ("buorre"); SET NP-HEAD-NOM = NP-HEAD-SG-NOM OR NP-HEAD-PL-NOM ; SET NP-HEAD-ACC = (Pron Acc) OR (N Acc) OR (A Acc) - RCmpnd - (Dem Attr) - ("buorre"); SET NP-HEAD-GEN = (Pron Gen) OR (N Gen) OR (A Gen) - Der/NomAct - RCmpnd - (Dem Attr) - ("buorre") ; #!! !The PRE-NP-HEAD family of sets #!! These sets model noun phrases (NPs). The idea is to first define whatever can #!! occur in front of the head of the NP, and thereafter negate that with the #!! expression __WORD - premodifiers__. SET PRE-NP-HEAD = (Prop Attr) OR (Prop @>N) OR (A Attr) OR (ABBR Attr) OR ("buorre") OR (Pron Pers Gen) OR (N Gen) OR BUOT OR Num OR RCmpnd OR CC OR (Pron Dem) OR (Pron Refl Gen) OR (Indef Attr) OR (PrfPrc @>N) OR PrsPrc OR (A Ord) ; # The strict version of items that can only be premodifiers, not parts of the predicate SET PRE-NP-V = PrfPrc OR PrsPrc OR Der/NomAg OR Actio OR Der/NomAct OR (V A) OR (Prs Sg3) + Ind OR (Prs Sg1) + Ind OR (Imprt Du2) ; # to be used together with PRE-NP-HEAD before @>N is disambiguated SET NP-MEMBER = PRE-NP-HEAD OR N ; SET PRE-A-N = (Pron Pers Gen) OR (Pron Pers Acc) OR (Pron Indef) OR Num OR (A Ord) OR (Pron Dem) OR (Pron Refl Gen) OR (Pron Refl Acc) ; # Acc pga av manglende disambiguering tidlig i fila SET NOT-PRE-A-N = WORD - PRE-A-N ; LIST PUNCT-LEFT = (PUNCT LEFT) ; LIST PUNCT-RIGHT = (PUNCT RIGHT) ; SET PRE-APP = COMMA OR PUNCT-LEFT OR PRE-NP-HEAD ; # This set ist not only for what can # stand in front of appositions but also # postmodifiers. #!! The set __NOT-NPMOD__ is used to find barriers between NPs. #!! Typical usage: ... (*1 N BARRIER NPT-NPMOD) ... #!! meaning: Scan to the first noun, ignoring anything that can be #!! part of the noun phrase of that noun (i.e., "scan to the next NP head") SET NOT-NPMOD = WORD - PRE-NP-HEAD OR ABBR OR @CVP ; # This is the previous NPNH (npnh) set. # NOT-NPMOD = "NOT-PRE-NP-HEAD" SET NOT-NPMOD-ACC = NOT-NPMOD - Acc OR ABBR ; SET NOT-NPMOD-ACC-ADV = NOT-NPMOD - Acc - Adv OR ABBR ; # To be used in mappingrules, before the disambuation of Acc and Gen. SET NOT-NPMODADV = WORD - PRE-NP-HEAD - Adv OR MO; # NOT-NPMODADV = "NOT-PRE-NP-HEAD-OR-ADV" SET NOT-NPMODADV-INDEF = WORD - PRE-NP-HEAD - Adv - Indef ; ## NOT-NPMODADVI = " ...-OR-INDEF" SET NOT-NPMODADVII = WORD - PRE-NP-HEAD - Adv - Indef - Ill ; # Illative indir.obj. SET NOT-NPMODADVIIP = WORD - PRE-NP-HEAD - Adv - Indef - Ill - Pcle ; # <== is this our NOT-NPMOD set? SET NOT-NPMODCC = WORD - PRE-NP-HEAD - COMMA - LCRD ; SET NAPP = WORD - PRE-APP ; # SET TOLERANT-PRENPP = V ; (everything non-NP-head!) # ... Most sloppy BARRIERs # Set for NP with participle premodifier # ... IF *-1 X BARRIER NOT-NPMOD OR # LocComIll are ok, but only with a PrfPcc to the right #!! !Other negatively defined morphosyntactic noun sets SET NOT-N = WORD - N ; #SET NOT-A = WORD - A ; SET NOT-N-A = WORD - N - A ; SET NOT-NAPrfCC = WORD - N - A - CC - PrfPrc ; SET NOT-NP = VFIN-NOT-NEG OR ConNeg OR Inf OR Pcle OR Interj OR CS ; # The set NP-BOUNDARY is bigger. SET CLB_NOT-COMMA = CLB - COMMA OR PUNCT-LEFT OR PUNCT-RIGHT ; SET NOT-QMARK = WORD OR CLB OR PUNCT - QMARK ; SET W-NOT-ACC-GEN = WORD - Acc - Gen ; #!! !Noun sets #!! Nominal sets defined according to their morphophonological properties #!! Sets for lexeme homonymy (most of them are moved to where the actual rules are.) #!! The words in the set __N-PO__ can be both N and Po, the set takes that into account. #LIST N-PO = "áigi" "gaskan" "gaskka" "gaskkas" "guovddáš" "ovddas" "ráji" "vuostá" "guvlui" ; LIST N-PO = "áigi" "guovddáš" "vuostá" ; #!! !The LAHKA set family LIST LAGA = (".*bargo#lága"r) "spábbačiekčan#lága" ; LIST LAGALAHKA = (".*bargo#láhka"r) "spábbačiekčan#láhka" "sierraláhka" ; SET LAHKA = (".*láhka"r) - LAGALAHKA ; LIST LAHKA-MOD = "almennet" "almmolašvuohta" "apotehka" "arkiiva" "áhpenuohtástit" "álbmotoadju" "bargi" "bargobiras" "báikenamma" "bákti" "bátnedearvvašvuođabálvalus" "bivdu" "boazodoallu" "čázádat" "dálkkas" "dásseárvu" "deatnu" "dearvvašvuođabargi" "dearvvašvuohta" "dearvvašvuođafitnodat" "dearvvašvuođabargiidláhka" "dearvvašvuođaregisttar" "divššohasvuoigatvuohta" "doaibmi" "eana" "eanasuodjaleapmi" "eanavuovdin" "elliidsuodjaleapmi" "energiija" "fápmudus" "Finnmárku" "friddjasuohkan" "fuođđu" "gávpot" "geaidnu" "gearggusvuohta" "gielddadearvvašvuođabálvalus" "gielda" "gili#oppalašeana" "girku" "golli" "guollebiebman" "háhkan#konsešuvdna" "hálddašeapmi" "heaggadieđut" "huksen" "industrikonsešuvdna" "jávrebivdu" "joatkkaoahpahus" "johtolat" "konsešuvdna" "kulturmuitu" "lavdnjeloggut" "lotnolasealáhusabargi" "luodda" "luonddusuodjalus" "luopmu" "luossa" "mánáidgárdi" "mánáidsuodjalusbálvalus" "mearraguolásteapmi" "mearraresursa" "minerála" "mohtorjohtolat" "muddet" "namma" "Norga" "norga" "oahpahallat" "oahpahus" "oahppu" "oassálastinláhka" "olgunastin" "olmmošvuoigatvuohta" "oktasašsápmi" "pasieantavuoigatvuohta" ("ráŋggáštit" Der/NomAct) "resursahálddašeapmi" "riekteveahkki" "sáivabivdu" "sápmi" "searvan" "sierra" "spesialistadearvvašvuođabálvalus" "stáhtaborgárriekti" "stáhtafitnodat" "tuollu" "uhccimusmihttonjuolggadus" "varasguolli" "várri" "vearrodahku" "vearru" "vuođđu" "vuođđoskuvla" "vuovdedoallu" "vuovdegáhttet" "vuovdi" "1789" "1842" "1863" "1888" "1899-#bivdu" "1899" "1920-#várri" "1933" "1965" "1975-#várri" ; # This list is for lahka compounds written with two single words LIST LAHKA-A = "boaris" "dálá" "dáláš" "gustojeaddji" "gustovaš" "našunála" "ovdalaš" "sorjjasmeahttun" ("suodjalit" Der/PassL PrfPrc) ; LIST LAHKA-V = "addit" "áimmahuššat" "árvalit" "ásahit" "čállit" "čuovvulit" "čuovvut" "dohkkehit" "gáibidit" "geatnegahttit" "geavahit" "gieđahallat" "jorgalit" "kriminaliseret" "mearridit" "muhttit" "ovddidit" "ráŋggáštit" "viiddidit" ; LIST LAHKA-V-PASS = "atnit" "ásahit" "báhkkodit" "báhkkot" "čállit" "čuoldit" "dadjat" "dahkat" "dohkkehit" "duššadit" "eaktudit" "fámuhuhttit" "geatnegahttit" "jorgalit" "jurddahit" "jurddašit" "kriminaliseret" "mearridit" "muddet" "njulget" "oaivvildit" "rievdadit" "ráŋggáštit" ; # This one works in combination with others, f.in. LAHKA-POST. LIST LAHKA-N = "§" "almmolašvuohta" "eanagirji" "eanangirji" "eatnangirji" "čađaheapmi" "fápmudus" "fápmuiboahtin" "gáibádus" "geatnegasvuohta" "geavaheapmi" "gonagas" "hálddašangeavat" "juksanmearri" "kap" "kapihtal" "konvenšuvdna" "láhkaásahus" "láhkaovdabargu" "láigohanvuoigatvuohta" "mearrádus" "njuolggadus" "nr" "paragráfa" "riekteáddejupmi" "riektegáldu" "riektegeavat" "riektesubjeakta" "sámekonvenšuvdna" "vuoigatvuođabargu" "vuoigatvuohta" ; # This one does it more likely to be "láhka" in combination with f.i. LAHKA-V: LIST LAHKA-SUBJ-N = "eiseváldi" "guovddášeiseváldi" "stáhta" ; LIST LAHKA-GEN-N = "§" "buohkaidvuoigatvuohta" "cealkka" ("fápmu" Ill)"hápmi" "johtolatvuoigatvuohta" "kapihtal" "láhkavuođđu" "ovdabargu" "rámma" "ráhkkananbargu" "ráidu" "sátnemearkkašupmi" "ulbmilparagráfa" "vuođđu" "vuođđoeaktu" "vuolit" "V"; # "vuolit" is an adj. but suit pragmatically to the set. LIST LAHKA-ASAHUS = "alimusriekti" "Odeldiggi" "Stuoradiggi" "Stuorradiggi" "stuoradiggi" "stuorradiggi" "vuolleriekti" ; LIST LAHKA-POST = "bokte" "olis" "mielde" "vuođul" ; #!! !Nominal sets defined according to their semantical properties # ------------------------------------------------------------- # Here we will write what sets we have and how we divide them. #!! * Spatial noun sets. These nouns behave like postpositions LIST SPATIAL-N = "guovlu" "osku" "sadji" "vuođđu" ; # These nouns in essiv get @ADVL: LIST ESS-ADVL-N = "arvedálki" "arvi" "árga" "baika" "bajándálki" ("bassi" N) ("báhkka" N) "beaivvádat" "beaivvadat" "biegga" "bievla" ("buolaš" N) "borga" "čakčaseavdnjat" "čáppadálki" "čuoika" "čuovga" "cuoŋu" (".*dálki"r) "dulvi" "fiertu" "goalki" "guoldu" "mánoheahpi" "mierká" "muohta" "njáhcu" "obbadálki" ("seavdnjat" N) "varra" "veaigi"; # These nouns/adjectives in essiv can get @ADVL: LIST ESS-PROB-ADVL-N = ("bassi" N) "boaris" ("nuorra" N) ; #!! * Time sets # - - - - - LIST MANNU = (".*.máánu"r) ; # Duomma:ii LIST AIGODAT = "áigi" (".*áigodat"r) "álgoáigi" "bargoáigi" "soahteáigi" "soahtegaskaáigi" ; # Duomma:lea LIST VAHKKU-DUR = "álgojahki" "árrageassi" "beaivi" "jándor" "bodda" "čakča" "čakčageassi" "čakčaseavdnjat" "čuohtejahki" "dálvi" "diibmu" "eahketbodda" "geassi" "giđđa" "idja" "iđitbodda" "jahki" "jahkebealle" "jahkečuohti" "kaleanddarjahki" "loahppajahki" ("[0-9]*-#lohku"r) "maŋŋe#giđđa" "mánnu" "minuhtta" "minukta" "njealjádasjahki" "skuvlajahki" "tiibma" "vahkkoloahppa" "vahkku" ; # these are periodes and can be Acc LIST VAHKKU-TIME = "b" "beassážat" "biidnovahkku" "bievlajahki" "bivdoáigi" (".*beaivi"r) "d-beaivi" "dienasjahki" "doaibmajahki" "eamiálbmotjahki" "earrejahki" "gaskaidja" "geardi" "juovllat" "juovlabassi" "luomejahki" "luopmojahki" "mihcamárat" "muorjejahki" "nissonjahki" "stuorradiggeáigodat" "vuoitojahki" "vuođđoskuvla#vahkku" ("[0-9]*-#jahki"r) ("[0-9]*-#jahki"r) "[0-9]*-[0-9]*-#jahki" "[0-9]*-[0-9]*-#lohku" ("[0-9]*-#lohku"r) ("[0-9]*-#lohku"r) "eahket" "iđit" ; # The quoteless jahki here is since the preprocessor is not fine-tuned # yet, it still gives '"1870-" # jahki N Sg Com'. # lets see if "dbm" works # Duomma:lea SET VAHKKU = VAHKKU-DUR OR VAHKKU-TIME ; LIST JAHKI-NUM = "jahki" "skuvlajahki" ; # Years which can be numerated LIST PARTTIME = "čavčča#bealle" ; # This set is for finding Gen in expressions like PARTTIME OR TIME Gen. LIST AIGI = "áigi" (".*náigi"r) ; LIST SP-BEAIVI = "albmáimannan#beaivi" "bargočoahkkin#beaivi" "beassášbeaivi" "mánnodat" "vuossárga" "disdat" "maŋŋebárga" "gaskavahkku" "duorastat" "bearjadat" "juovlabeaivi" "lávvardat" "lávvordat" "sotnabeaivi" "sábbát" "skilleduorastat" ; LIST GEN-BEAIVI = "álbmotbeaivi" "árgabeaivi" "bargobeaivi" "beaivi" "duopmobeaivi" "riegádanbeaivi" "skuvlabeaivi" ; # General-beaivi can have Gen modifier, like "skuvlla árgabeaivi". #LIST DATE1 = ("[0-3][0-9]\.[0-1][0-9]\.[0-3][0-9][0-9][0-9]"r) ("[0-3][0-9]\.[0-1][0-9]\.[0-9][0-9]"r) ("[0-9]\.[0-1][0-9]\.[0-3][0-9][0-9][0-9]"r) ("[0-3][0-9]\.[0-9]\.[0-3][0-9][0-9][0-9]"r) ("[0-9]\.[0-9]\.[0-3][0-9][0-9][0-9]"r) ("[0-3][0-9]\.[0-3][0-9]"r) ; #SET DATE = DATE1 - ("[0-9]*"r) ; # En litt klosset måte å gjøre det på, fikk ikke regex i DATE1 til å fungere som de skulle SET BEAIVI-REF = SP-BEAIVI OR GEN-BEAIVI OR Sem/Date ; LIST BEAIVI = "beaivi" "b" ; LIST YEAR = ("[0-2][0-9][0-9][0-9]"r) ; SET TIME = MANNU OR VAHKKU OR BEAIVI-REF OR AIGI OR YEAR ; # Do not add AIGODAT, it has some other characteristics in some cases. # But fix!! # "Sámediggeráđđi lea áigodagas doallan 5 čoahkkima." # Today believed to be obj. SET NOTIME = N - TIME ; LIST GEASSET = "dálvet" "dálvit" "giđđat" "geasset" ("geassit" Adv) "čakčat" ; # What is special here? LIST PAST-MARKER = ("mánná" Ess) "dalle" "diibmá" "dolin" "dološ" "dovle" "duvle" "eske" "gieskat" "ikte" ("nuorra" Ess) "ovdal" ("ovdditbeaivi" Gen) ("vássánáigi" Loc) ("boaresáigi" Gen) ; LIST PRESENT-MARKER = "dál" "ihttin" "odne" "otne" ("boahtteáigi" Loc) ("boahtteáigi" Gen) ; SET TIME-MARKER = PAST-MARKER OR PRESENT-MARKER ; LIST OTHER-TIME-ADV = "árabuš" "árrat" "dál" "diibmá" "easkka" "easka" "guhká" ("guhkit" Adv) "maŋemustá" "maŋŋel" "maŋŋil" "maŋŋá" "maŋŋelaš" "maŋŋeleappos" "maŋŋit" "muhtumin" "ovdal" ; SET TIME-ADV = TIME-MARKER OR OTHER-TIME-ADV OR GEASSET; LIST PLACE-PO = "duohken" ; #!! * Amount sets LIST VOLUME = "cl" "lihtar" (".*lihtter"r) "dl" "lihtter" "ml" ; LIST WEIGHT = "mg" "kg" "kilo" "kilu" "gilo" "tonna" ; LIST LENGTH = "čuoldabadji" "dumá" "fierbmebadji" "gaska" "miila" (".*mehtar"r) (".*mehter"r) "mehtar" "mehter" "sente" "cm" "tumá" "állan" "salla" "gaska" ; LIST TEMPERATURE = "buolašceahkki" "buolašgráda" "lieggaceahkki" "lieggagráda" ; LIST AMOUNT = "uhcánaš" "unnánaš" ; LIST TIME-UNIT = (".*jahki"r) "minuhtta" "minukta" "sekunda" "vahkku" "mánnu" "diibmu" "beaivi" ; # For use for rules hitting "maŋŋel" as Adv instead of Po. Also in MEASURE-set. SET MEASURE = VOLUME OR WEIGHT OR LENGTH OR AMOUNT OR TEMPERATURE OR TIME-UNIT ; LIST CURRENCY = "denara" "dollár" "euro" "kruvdnu" "kr" "ru" "rubel" "ruvdno" "ruvdnu" "¢" "€" "$"; SET CURRENCY-GEN = CURRENCY + Gen ; LIST NUMUNIT = "čuohti" "duhát" "miljovdna" "mill" "milj" "miljárda" "miljon" "mrd"; LIST KIND = (".*šládja"r) ; LIST COUNTABLE = "oassi" "kapihtal" "paragráfa" ; LIST NUMMAR = "identifiserennummar" "njuolggotlf" "nr" "nummar" "nummir" "tabeallanummar" "vuorkááššenr" ; LIST KLASS = "ášši" "bálkáceahkki" "čuokkis" "s" "siidu" "§" "§§" "paragráfa" "oassi" "kap" "kapihtal"; LIST PEOPLE-NUM = "guovttis" "golmmas" "njealjis" "viđas" "guđas" "čiežas" "gávccis" "ovccis" "logis" ; LIST GUOVTTIS = "guovttos" (".*guovttos"r) "guovttis" ; #!! * Sets for nouns with morpho-syntactic preferences # ---------------------------------------- #!! * Number-related sets LIST PL-N = "áiru" "beaivváščalbmeláset" "beassážat" "biddu" "čalbmeláset" "čázet" "fáhcca" "gállot" "gálssot" "gáma" "gistta" "goikket" "gummestevvel" "heajat" "hellodagat" "juovllat" (".*mállásat"r) "nagir" "njealljejuvllat" "njuorjjot" "nuhtat" "nuvttat" "nuvttot" "sabet" "sáppat" "sisttet" "skárrit" "skierat" "skuovva" "stevvel" "suohkku" "suorbmafáhcca" "suorpmahat" "ullofáhcca" "ullosuohkku" "vuotta" "viljjit" ("[0-9]*-#jahki"r) ("[0-9]*-[0-9]*-#jahki"r) ("[0-9]*-#jahki"r) ; # Nominals that appear with plural numerals. LIST SG-WORD = ("addit" Der/upmi) "almmolašvuohta" "anistupmi" "arvi" "áigemearri" "álgu" "áŋgirvuohta" "ávvu" "ballu" "bargguhisvuohta" "bággu" ("bávččas" Der/vuohta) "boazodoallu" "borakeahttáivuohta" "buorredáhtolašvuohta" (".*deaddu"r) "diehtemeahttunvuohta" "doaivu" "doarjja" "dárogiella" "duhtavašvuohta" "Finnmárkoláhka" "fuolalašvuohta" "gaskkamuddu" "gávvilvuohta" "geargatvuohta" "geardun" "geavaheapmi" "gelbbolašvuohta" "giellageavaheapmi" "gihtta" "giitevašvuohta" "gudnejahttin" "fápmu" "guossoheapmi" "guovttegielalašvuohta" "hearvásvuohta" "iešdovdu" "illu" "imaštallan" "ipmilbalolašvuohta" "ipmárdus" "isitvuohta" "juonalašvuohta" "kulturduogáš" "kulturgelbbolašvuohta" "láhkavuođđu" "luondu" "luondduvuođu" "loahppa" "máŋggabealatvuohta" "mielki" "miella" "šlundi#miella" "miellasuvvan" "moraš" "muohta" "musihkka" "oamedovdu" "olahahttivuohta" "ovddasvástádus" "ovttasbargu" "ovttajienalašvuohta" "ovttadássásašvuohta" (".*politihkka"r) "ráffi" "ráfi" "rabasvuohta" "ráhkisvuohta" "rávisvuohta" "riska" "roahkkatvuohta" "sámegiella" "sámegielmáhttu" "sámekultuvra" "ustitvuohta" "vanhurskkisvuohta" "vásáhusduogáš" "veahkaválddálašvuohta" "vuohki" ("vuordnut" Der/NomAct) "vuosteháhku" ; # Words that are used in singular unless their plurality is stressed by words such as "goappeš", "goappašat", "earálágan", "máŋgalágan" or Num or Ord. #!! * Sets for case, possessive, etc. LIST LOC-N = (".*dilálašvuohta"r) "dáhpáhus" "ipmárdus" ; # Those nouns appear in locative unless a head asks for comitative. LIST VUOHKI = (".*vuohki"r) ; # Usually in comitative, see rule LIST N-NOPXLIST = "atnu" "almmolašvuohta" "áibmu" "áigemearri" "áigi" "álbmotjienasteapmi" "álgoálgu" "álgostávval" "álgu" "álki" ("árvidit" Der/NomAct) "bargoáigi" "báhkka" ("beaivádit" Der/NomAct) "bievlajahki" "boahtteáigi" "boahtu" "boazodoallu" "boraspire" ("buorre" Comp) "cealkka" "čakča" "čakčageassi" "čáppagirjjálašvuohta" "čiegus" "čiehča" "dálvi" "dáža" "divregiksi" "dollagáddi" "dološ" "duo" "eahket" "fylkkamánni" "fylkkaviessu" "Finnmárkkuopmodat" "geatnegas" "geavahanriektelaš" "geavat" "gaskkamuddo" "gárvi" "geassi" "genitiivahápmi" "giđđa" "giellageavaheapmi" "girkosiida" "hálddašanguovlu" "háldejaš" "hoahppu" "historjá" "jahki" "japma" "jođán" "johgáddi" "johtu" "kilo" "láhka" "leansmánneárvvošteapmi" "loahppa" "logaheapmi" "lohku" "lohpi" "luondu" "maŋŋi" "máŋggaidlohku" "meallu" "meannudeapmi" "mielladearvvašvuođa#dikšu" "muitu" "njunuš" "nuoraidskuvladássi" "nuppádas" "nuppát" ("oahpahit" Der/NomAct) "oasálaš" "ođas" "ođđajahki" "oktavuohta" "olámuddu" "olle" "olmmoš" "ortnet" "ovttaidlohku" "ovttasbargu" "predikatiiva" "ráfi" "rávásmanahki" "riektegeavat" "riikkaarkivára" "sápmelaš" "sisriika" "sivva" "Skjerstad-ášši" "smávvaskuvladássi" "soaittáhat" "stáhtaráđđi" "stuorradiggi" "suohtta" "várá" "unnitlogugiella" "vahkku" "valljodat" "viiddis" "viso" ("[0-9]*-#lohku"r) Coll ; # atnit muittus / árvvus # Nominals that probably do not have a Px ('1600-logus'). LIST N-PX = "áhčči" "bárdni" "beana" "biigá" "boadnji" "eadni" "eammi" "gáibmi" "guoibmi" "hearrá" "nieida" "oabbá" "olmmái" "ráhkis" "reaŋga" "skibir" "skihpár" "ustibaš" "ustit" "viellja" ; # Nominals that well may have a Px. LIST ALU = "alu" "gasu" "govddu" "guhku" "losu" "stuoru" "viiddu" "čieŋu" ; # Those are words that only appear in one form, which Nickel calls A/G. # They are only in a predicative position. # These are ABBR: LIST REAL-TITLE = "prof" "cand.mag" "cand.oecon" "cand.philol" "cand.real" "cand.scient" "cand.theol" "cand" "dr.art" "eksp.hoavd" "eksp.sj" "fenr" "fig" "fil.tri" "gen.lt" "genr" "genr.lt" "h.r.adv" "hr" "kapt" "korp" "lekt" "lic" "ltn" "mag.art" "mag" "merc" "miss" "Mr" "mr" "Mrs" "mrs" "odont" "oecon" "ordf" "ossod.dir" "stud.phil." "res.kap" "stud.philol" "vit.ass" "dr" "dr.med" "dr.philos" "dr.theol" ; LIST TITLE-LIKE = "gásttašeaddji" "justitiarius" "majestehta" "miss" "ránnjá" ; # Ránnjá Ole Vuolab imašta manne .... #!! * Sets for nouns as pred # subcategorizing for a particular case LIST LOC-COMPL-N = "ávki" "árvalus" "dovdu" "ipmárdus" "ovdamearka" "sáhka" ; # Nouns that take a locative # There is also an idiomatic use of "ovdamearka" in the constructions "ovdamearkka dihte" and "ovdamearka" (Ess). LIST COM-COMPL-N = "ákkastallan" "bargu" "čoahkkin" "dahkamuš" "dárbbašmeahttun" "dearvuohta" "deaivvadeapmi" "digaštallan" "duhkoraddan" "earrodearvvuođat" "earru" "gaskavuohta" "lihkku" "oktavuohta" "oktiibidjan" "ovttaoaivilis" "ovttasbargočoahkkin" "ovttasbargu" "ovttastallan" "ovttasássi" "ovttasbargošiehtadus" "ovttastus" "ságastallan" "šiehtadus" "vuostálaga" ; SET LOC-HEAD = LOC-V OR LOC-COMPL-N ; SET COM-HEAD = COM-V OR OKTII-V OR COM-COMPL-N ; LIST PREGEN = "álggogeahčen" "beallemuttus" "beallemuddu" ("bealli" N Sg Loc) "gaskamuddu" "gaskkamuddo" "gaskkamuddu" ("gaskavuohta" N Sg Loc) "loahpageahčen" "loahpa#geahči" "oktavuohta" "ovttasbargu" ; # Nouns and adjectives that take a preceding genitive. # Possessor hierarchy # + P o s s e s s e d | # Possible possessors + FAMILY FAMILY-ALSO-ABSTRACT NON-FAMILY + # ------------------------ + -------- ----------------- ------------ | # Prop Sem/Plc + x x | # HUMAN-INDIVIDUAL + x x x | # FAMILY pronouns + | # HUMAN-GROUP + x | # PROFESSION + x x x | # OFFICE + x x x | # HUM-FUNCTION + x x x | # ABSTR-TEXT + x x x | # PLACE (not NATURE-PLACE) + x x | # NATION + x x | # ANIMAL + x | # EDUCATION + x x | # ORGANIZATION + x x | # INSTITUTION + x x | # INDUSTRY + x | LIST FAMILY-ONLY-HUMAN = (Prop Sem/Mal) (Prop Sem/Fem) (Prop Sem/Sur) "áddjut" "áhkká" "áhkkut" "bárdnemánná" "boadnji" "čeahci" "čeahcit" "dálueamit" "eahki" "eamit" "eammi" "eanu" "goaski" "guoibmi" "ipmi" "irgi" "isit" "lunta" "mánáidmánná" "mannji" "máhka" "máttaráddjá" "máttaráhkku" "moarsi" "muoŧŧá" "muoŧŧal" "náittosguoibmi" "neahpi" "oabbá" "oabbábealle" "oambealle" "oappáš" "oarpmealle" "osku#guoibmi" "ristváhnen" (".*sássa"r) "siessal" "siessá" "vieljaš" "viellja" "vielljabealle" "vilbealle" "vuohppa" "vuonáhkku" "vuoni" ; # These can only be possessed by HUMAN-INDIVIDUAL, HUMAN-GROUP, PROFESSION, OFFICE, HUM-FUNCTION, ABSTR-TEXT LIST FAMILY-ALSO-ABSTRACT = "áhčči" "áddjá" "áhkku" "bearaš" "eadni" "oapmahaš" "sohka" "sohkagoddi" "váhnen" "veahka" ; # These can be possessed by HUMAN-INDIVIDUAL, HUMAN-GROUP, PROFESSION, OFFICE, HUM-FUNCTION, ABSTR-TEXT, PLACE (minus NATURE-PLACE), Prop Sem/Plc, NATION, ANIMAL, EDUCATION, ORGANIZATION and INSTITUTION. Can also be used as metaphors. # Giellaplánaid eadni. SET FAMILY = FAMILY-ONLY-HUMAN OR FAMILY-ALSO-ABSTRACT ; LIST NON-FAMILY = "bárdni" "bártnáš" "divššohas" "gánda" (".*guoibmi"r) "guossi" "kránnjá" "lagamuš" (".*mánná"r) "mánáš" (".*nieida"r) "nieiddaš" (".*nisson"r) (".*nisu"r) "nuorra" "oskkuviellja" "olmmái" (".*olmmoš"r) "ránnjá" "rumaš" "sámenuorra" "sápmelaš" "skibir" "skihpár" "smávvagánda" (".*ustit"r) "verdde" "viissis" ; # These can be possessed by HUMAN-INDIVIDUAL, HUMAN-GROUP, PROFESSION, OFFICE, HUM-FUNCTION, ABSTR-TEXT, EDUCATION, PLACE (minus NATURE-PLACE), Prop Sem/Plc, NATION, EDUCATION, ORGANIZATION, INSTITUTION and INDUSTRY. LIST HUMAN-LIKE = "beahtu" "beargalat" "eŋgel" "háldi" "hearrá" "ipmil" "stállu" "suodjalus#eŋgel" "ulda" ; # This set is used in Gen/Acc-rules. LIST SAPMI = "davvisápmi" "julevsápmi" "lullisápmi" "máttasápmi" "mearrasápmi" "nuortasápmi" "oarjesápmi" "sápmi" "Sápmi" ; SET HUMAN-INDIVIDUAL = HUMAN-LIKE OR FAMILY OR NON-FAMILY OR Sem/Hum - SAPMI OR ("gii") OR ("guhte") ; LIST HUMAN-GROUP = "álbmot" (".*álbmot"r) (".*bearaš"r) (".*čearda"r) "delegašuvdna" "gázzi" (".*guovttis"r) (".*guovttos"r) (".*joavku"r) (".*kommišuvdna"r) (".*komiteá"r) "ráidu" "ráđđi" ("sápmi" N Pl) "unnitlohku" (".*veahka"r) (Sem/Group_Hum) ; ## group of humans that connot be a building at the same time LIST PROFESSION1 = (".*advokáhta"r) (".*advokáhtta"r) (".*duopmár"r) "arkeologa" (".*artista"r) (".*assisteanta"r) (".*áittardeaddji"r) "ákšoalmmái" (".*bargi"r) "buorideaddji" "ámmátolmmái" "ámmátolmmoš" (".*mánni"r) (".*hoavda"r) (".*meannudeaddji"r) (".*geahčči"r) (".*bagadalli"r) (".*bagadeaddji"r) (".*konsuleanta"r) "bargoveahka" "bassaleaddji" "bassi" "báhkár" "báhppa" "bálvaleaddji" (".*čálli"r) "bearremánni" "bibliotekára" (".*biigá"r) ("biila#divvut" Der/NomAg) (".*vuovdi"r) "birasgáhttenráđđeaddi" (".*terapevta"r) (".*terapeuta"r) "bisma" "bismá" "bispa" (".*bivdi"r) (".*hábmejeaddji"r) "boanda" "boazodoalli" "boazosápmelaš" "boazosápmi" "bolesmeašttir" (".*vuoddji"r) "buvttadeaddji" "čalbmeáhkku" "čalbmeeadni" "čálaoahppavaš" "čiekči" "čorgejeaddji" (".*čuojaheaddji"r) "dáidár" (".*dáiddár"r) "dálon" "dálueamit" "dáluisit" "dárkkisteaddji" "davvisápmi" (".*dikšu"r) (".*direktevra"r) (".*dirigeanta"r) (".*divššár"r) (".*doaimmaheaddji"r) (".*doavttir"r) "dulka" "duojár" (".*duopmar"r) (".*dutki"r) "ealáhusdoalli" "eallo#doalli" "eanadoalli" "eananhearrá" (".*sadjásaš"r) "eatnandoalli" "fáldi" "fitnodatdoaibmi" "fitnodatoamasteaddji" "gávpejas" "giellaráđđi" (".*veahkki"r) "girdi" "girko#bálvaleaddji" "girkodulka" "gollerávdi" "gonagas" "govvadáidár" "govvejeaddji" "guođoheaddji" "guolásteaddji" "hárjeheaddji" (".*teknihkar"r) (".*jođiheaddji"r) "johttisápmi" "johttisápmelaš" (".*journalista"r) "keaisár" "kirurga" "koahkka" "kuráhtor" "korefereanta" "kursaoahppi" "lágideaddji" "láibu" "lávlu" "leanut" "logopeda" "luhkkár" "máilmmemeašttir" "máhttájeaddji" "máttasápmi" "mearraalmmái" "mearraolmmái" "mearrasápmi" "mišuneara" "museá#bargi" "musihkkadahkki" "musihkkár" "návetvázzi" "neavttár" "njunušjurista" "noaidi" "offiseara" (".*oahpahalli"r) (".*oahpaheaddji"r) "oahppi" ("oaivadit" Der/NomAg) "oaivámuš" "ođashoavda" "ođaslohkki" "ossodatdirektevra" "ossodatdirektøra" "parkerenfákta" "pedagoga" "plánejeaddji" "poliisa" "politiija" ("prentet" Der/NomAg) "profehta" "professor" "rádjefákta" "rádjesoalddát" "ráđđeaddi" "ráđđeolmmái" "reainnár" "rávdi" "reaŋga" "redaktevra" "rehketdoallodárkkisteaddji" "rehketdoalli" "rektor" "ruhttejeaddji" "ruvdnaprinsa" ("ruvvet" Der/NomAg) "sámediggeráđđi" "sámeduojár" "sárdnideaddji" "sávzadoalli" "sealgeeadni" "sester" "silbarávdi" "snihkkár" "soalddát" "sosionoma" "spábbačiekčanhárjeheaddji" "spábbačiekči" "stipendiáhta" "studeanta" "sundi" "suohkanbáhppa" "suohkan#plánejeaddji" "šibitdoalli" "taksivuoddji" "telefonvástideaddji" "tuollár" "turistaofelaš" "uksafákta" "universitehtalektor" "váldodoaimmaheaddji" "viessohoiddár" "vuoktačuohppi" ; SET PROFESSION = PROFESSION1 - Prop ; LIST OFFICE = "áirras" "ámtamánni" "bajitbáhppa" "boazodoallohoavda" (".*čálli"r) "dekána" "farao" "fylkkaráđđi" "gonagas" "leansmánni" "minister" "ministtar" (".*ministtar"r) (".*minister"r) "nissonáirras" "politihkar" "politihkkár" "prinseassa" "ráđđeláhttu" "ruvdnaprinseassa" "ságadoalli" "Sámedemokráhtta" "sámedikkeáirras" "Sámediggepresideanta" "sámediggepresideanta" "sátnejođiheaddji" "stivralahttu" "ovdaolmmoš" "presideanta" "stáhtaráđđi" "várrepresideanta" ; SET TITLE = REAL-TITLE OR TITLE-LIKE OR PROFESSION OR OFFICE OR Actor ; LIST HUM-FUNCTION = "Bergen-soalddát" "buohcci" "divššohas" "kandidáhtta" "kandidáhta" "nomáda" "oahppanolmmoš" "oktavuođaolmmoš" "olbmobárdni" "pasieanta" "ráđđealmmái" "riika#vuloš" "sámedemokráhtta" "skohtervuoddji" "soahteolmmái" "stáhtaboargár" "suttolaš" "turista" "virgeguoibmi" "virgeolmmoš" "vuorasolmmoš" ; #XXX bad name # Don´t add veahkki + Ess. LIST HUM-ATTR = "bassi" "divššohas" "eananeaiggát" "eaiggát" "eatnigielhálli" "fástaássi" "gávttehas" "informánta" "lestadiánalaš" "sámegielat" "suttolaš" ; # adjectival LIST HUM-VERB = "ássi" "boaris" "bálvaleaddji" "bálvalanguoibmi" "boazoeaiggát" "dállodoalli" "eananeaiggát" "geavaheaddji" "gili#ássi" "muitaleaddji" "ovttasássi" "riikkaássi" "vuotnaássi" "vuostebelle" "vuostebealli" ; # vearbal LIST NATIONAL-IDENTITY-NOT-SAPMI = "badjesápmelaš" "dáčča" "dánskalaš" "dáža" "duiskalaš" "Enodatsápmelaš" "Guovdageainsápmelaš" "guovdageaidnolaš" "hollándalaš" "indiána" "israellaš" "judálaš" "juvddálaš" "julevsápmelaš" "kvena" "lullisápmelaš" "maya-#indiána" "njávdánsápmelaš" "nuortalaš" "oarjesápmelaš" "olgoriikalaš" "palestinalaš" "romalaš" "romer" "ruotasuopmelaš" "ruošša-#sápmelaš" "samarialaš" "siseatnansápmelaš" "Suonjilsápmelaš" "Várjjatsápmelaš" "vuotnasápmelaš" ; # Also regional identity # Duomma:lea LIST SUOPMA = "Davvi-Ruoŧŧa" "Davvi-Suopma" "Lulli-Ruoŧŧa" "Lulli-Suopma" "Mátta-Ruoŧŧa" "Mátta-Suopma" "Oarje-Ruoŧŧa" "Oarje-Suopma" "ruošša" "Ruošša" "ruoŧŧa" "Ruoŧŧa" "suopma" "Suopma" ; # This set is used in Gen/Acc-rules. # Duomma:lea SET NATIONAL-IDENTITY = NATIONAL-IDENTITY-NOT-SAPMI OR SAPMI ; SET HUMAN = HUMAN-INDIVIDUAL OR HUMAN-GROUP OR PROFESSION OR HUM-FUNCTION OR HUM-ATTR OR HUM-VERB OR OFFICE OR Sem/Hum ; SET NOT-HUMAN = N - HUMAN ; #!! * Sets for animals LIST GEN-ANIMAL = "ábegáhttu" "ásen" "beana" "bohkká" "bussá" "čeavrris" "ciiku" "čivga" "dámmá" "ealit" "fuođđu" "gáhttu" "gáica" "gálbi" "gihcci" "guigu" "gussa" "heasta" "horti" "láppis" "loddi" "máhtu" "njiŋŋálas" "ore" "sávza" "sávzabeana" "smávvafuođđu" "spiinnečivga" "spiidni" "vársá" "vársi" "vielppis" "vierca" "vuoksá" "vuoncávaris" "vuonccis" Sem/Ani ; LIST PREDATOR = "gumpe" "guovža" "bierdna" "geatki" "albbas" ; LIST HUNT-ANIMAL = "ealga" "rievssat" ; LIST BOAZU = "áldu" "boazu" "čearpmat" "čora" "eallu" "heargi" "miessi" "sarvvis" "vierroboazu" "vuonjal" ; LIST FISH = "bálddis" "čuska" "dápmot" "diddi" "diksu" "dorske#guolli" "dorski" "duovvi" "gilot" (".*guolli"r) "hávga" "juksu" "luosjuolgi" "luossa" "luossaguolli" "luossanálli" "muortu" "sallit" "sáidi" "sáivaguolli" "šákša#dorski" "stábbasáidi" "stáinnir" "stuorasáidi" "rutnot" "veajet" ; LIST BIRD = "ákta" "báiski" "bovttáš" "cagan" "čearret" "gádde#loddi" "gáiru" "mearaloddi" "skávli" "skuolfi" "šuoršu" "albatrossa" "alitbađuš" "alitgaccet" "alitoaigaccet" "bakku" "bastesuorsi" "bađošgaccet" "beahcebáhcatloddi" "beahceloddi" "bealdocihci" "bealdo#garjá" "bealdo#vuorra" "bealgeloddi" "beallje#loađgu" "bealljerásttis" "bearalskuolfi" "beasterages" "beibboš" "beibbošcihci" "beibbošcizáš" "belddoš#vizar" "beškkoš" "beštor" "bieggafálli" "biehkan" "bigán" "bihcabasčáihni" "bihcebasgáski" "bihcebasčáihni" "bissehávka" "bižus" "boaimmáš" "boallonjukča" "boađđocivkkán" "borjjastit" "borsenjunni" "bovttáš" "bulddogas" "bumbá" "buoidegaccet" "buokčat" "buokči" "bupmálaš" "bursanjunni" "bussáskuolfi" "buvvedat" "báiski" "bákteduvvá" "bárbmofálli" "bávgoš" "cagan" "cagán" "cielláš" "cihceskuolfi" "cihrrelastavizar" "civkaleivvoš" "cizášfálli" "cizopaš" "cizot" "davvelastavizar" "davveloddi" "davvevizar" "deaggačáihni" "deagge#báiski" "deaggecihci" "dearbmerásttis" "derpmoš" "dieldá" "dielkoduvvá" "dihtti" "diksobáhppa" "dirre#lihká" "doadjosuorsi" "dokta" "dovtta" "duoršu" "duottarbižus" "duottarcivkaleivvoš" "duvvá" "duvvárásttis" "dálvebeštor" "dálveruoivil" "dálvi" "dážaboaimmáš" "dážasuorsi" "fasána" "fiehta" "fiervá#vierru" "fierváviroš" "fiskesbeštor" "fiskescihci" "fiskescižáš" "fiskesgaccet" "fiskesjievžžan" "fiskesnjungáhkkor" "fiskesvizar" "fiŋka" "gaccepaš" "gaccet" "gahperbáiski" "gahpervizar" "garjá" "gassa#njunni" "gazzaloddi" "gazzebiehtár" "geađgejorgu" "geađgerásttis" "giega#biigá" "giehka" "giehpa#vuonccis" "giellavealgu" "gierdo#duvvá" "gierdorásttis" "gierdosuorsi" "gierdo#čuonjá" "gierra" "giljobaš" "gilljobaš" "gilvabeštor" "girjebáhcatloddi" "girjelivkkár" "giron" "goahcce#loddi" "goahppil" "goahppil#gálli" "goahtegoljaš" "goalsi" "goalsoruoššehas" "goalšovizar" "goarga" "goargaloddi" "goargŋohaŋŋá" "goaski" "goaskin" "gollaš" "gollebeibboš" "gollecihci" "golle#gahpir" "golli" "golláš" "gorges#hávda" "gorgeslihkká" "govuskuolfi" "gođa#loddi" "gožu#vuoražas" "guoikgáhrit" "guoikgárri" "guoksa" "guolbba#vierru" "guolbbaviroš" "guolbba#čoavžžu" "guollefálli" "guollečearret" "guorga" "guossabáhcatloddi" "guossagaccet" "guossaruossanjunni" "guossavizar" "guovssat" "guovssoloddi" "gussagoalsi" "guškil#vierru" "guškil#viroš" "guškkástat" "gáddebuvvet" "gáddeskirvi" "gádde#vierru" "gáddeviroš" "gáhkkor" "gáiru" "gállat" "gálli" "gállit" "gáranas" "gáranas#loddi" "gárggogoalsi" "gárgo#goalsi" "gávlačuonjá" "hálkaloddi" "haŋŋá" "heartavizar" "hoaššacihci" "hurrat" "hurri" "hurri#goahppil" "hurri#čukčá" "háigir" "háigir#loddi" "hálka" "hálkagonagas" "hálka#čielkkis" "háskil" "hávda" "idja#skuolfi" "jeaggefálli" "jeaggemeahkástat" "jeagge#čoavžžu" "jeaggehávut" "kanárialoddi" "keaisár#pingviidna" "jiekŋačielkkis" "jiesmi" "jievjaskuolfi" "jievželoddi" "jávresopmir" "leahttofálli" "leahttospálfu" "leaibeloddi" "leivvoš" "lidnu" "liidn-elláš" "liin-elláš" "litnut" "livkkár" "loađgu" "loddi" "loddegonagas" "loddejievži" "luhkka#loddi" "láfol" "láhtospálfu" "látteguoksa" "látteguovssat" "láttovuonccis" "láŋgá" "meahkástat" "mearragoaskin" "mearragáiru" "mearra#čuonji" "mearračuonjá" "miellespálfu" "miesttacihci" "miesttarásttis" "miesttavizar" "miesttašurrevizar" "moldecizáš" "muhkkecizáš" "muogir" "muorracivkkán" "muorragakcu" "mákreallačearret" "niehttegarjá" "niitocivkkán" "njukča" "njurggu" "njurgut" "noaideloddi" "nuortacihci" "nuortalastavizar" "nuorti" "náhkke#soadjá" "oanehisnjunčuonjá" "paradiisa#loddi" "pelikanloddi" "pingviidna" "ribeskáiti" "riddocivkaleivvoš" "riddo#vierru" "riddoviroš" "rievssat" "rievssatcižáš" "rievssatfálli" "roavgogonagas" "rohtogaccet" "rohtovizar" "rohtočoavžu" "rohtočoavžžu" "rukses#bađoš" "ruksesbeibboš" "ruksescivkaleivvoš" "ruksesfiehta" "ruksesguškil" "ruksesjuolčoavžžu" "ruksesruivil" "ruksesruoivil" "ruksesrásttis" "rukses#soadjá" "ruksessuorrehávut" "ruoivil" "ruonábeibboš" "ruonácihci" "ruonácizáš" "ruonájuolčoavžžu" "ruoná#čáihni" "ruossalas#njunni" "ruovddagas" "ruovdecihci" "ruovdecizáš" "ruođa" "ruoššaboaimmáš" "ruoššaskire" "ruošša#skirri" "ruoššaállat" "ránescihci" "ránescizáš" "ránesháigir" "ráneslivkkár" "ránesrásttis" "ránesskuolfi" "ránes#skávli" "ránessnárttal" "ránesčuonjá" "ránesčáihni" "rásttis" "rávgoš" "salletgáiru" "sallitgáiru" "seallecižáš" "siesse#mohkki" "sieđgacivkkán" "sildegáiru" "silkebuokča" "sitronbeštor" "skierru" "skilkeskálka" "skire" "skirri" "skiŋgegaccet" "skoarra" "skuolfi" "skutnjaloddi" "skáhpeloddi" "skáiti" "skárfa" "skárfa#čielkkis" "skávli" "snárttal" "soadja#njálla" "sopmir" "spoađđo#duoršu" "spálfu" "stoarbmaloddi" "stoarbmaspálfu" "stohkkegaccet" "stohkkerievdu" "stohkkespálfu" "stohpoháigir" "stohpospálfu" "struhcca" "struhccaloddi" "stuorrafiehta" "stuorragiljobaš" "stuorraguškil" "stuorraguškkástat" "stuorrameahkástat" "stuorraskáiti" "stuorraskávli" "stuorravuodja" "stuorravuojaš" "stuorračarkkus" "stuorračoavžu" "stuorračoavžžu" "stuorračuonjá" "stálobeibboš" "stárra" "suoidnesuorsi" "suoidnečiksa" "suolaskáiti" "suorrespálfu" "suorsi" "suotnjoliráš" "suotnjočoavžžu" "suovkacihci" "suvlá" "sáhcomeahkástat" "sáhpánboaimmáš" "sáhpánskuolfi" "sáiva#hávda" "sávjahávda" "sávza#loddi" "toardnagarjá" "toardnagájon" "uhcabuokča" "uhcabuvvedat" "uhca#báiski" "uhcaciellá" "uhcacihci" "uhcameahkástat" "uhca#njukča" "uhca#saddi" "uhca#vierru" "uhcaviroš" "uhca#čoavžžu" "uhca#čáihni" "ummolcizáš" "upmolcizáš" "unduláhtta" "uvlohávut" "varra#loddi" "veastareaddji" "vigláčoavžžu" "vilgesnierčuonjá" "vilges#soadja#skávli" "vilgesummolcizáš" "vilges#vierru" "vilges#viroš" "vilges#čoavžu" "vilges#čoavžžu" "vilgessealčáihni" "vintán" "vuoncáčivga" "vuoncávaris" "vizardit" "vuodja" "vuojaš" "vuoktafiehta" "vuoktagaccet" "vuoktagoalsi" "vuoktaláfol" "vuoktaskárfa" "vuonccis" "vuonccisloddi" "vuoražas" "vuorččis" "vuovdaduvvá" "vuovdecivkaleivvoš" "vuovdegaccet" "vuovdeloddi" "vuovdemeahkástat" "vuovderásttis" "vuovdevizar" "vuovde#vuorččis" "vuovde#čoavžu" "vuovdečoavžžu" "ábirievssat" "áhpedokta" "áhpedovtta" "áhpe#háskil" "áhpehávda" "áhpelihkká" "áhpespálfu" "ákta" "állat" "čarkkus" "čearret" "čiekčá" "čielkkis" "čierggesrásttis" "čiksa" "čoađgi" "čukčá" "čuohtegielas" "čuohtegiella" "čuonji" "čuonjá" "čuonjáfálli" "čáhcebávgoš" "čáhcevuonccis" "čáhppes#bađoš#guškil" "čáhppesbuokča" "čáhppessealbeštor" "čáhppesgaccet" "čáhppesrásttis" "čáhppesčoavji" "čáhppes#čoavžu" "čáhppesčoavžžu" "čáihnecizáš" "čáihnegaccet" "čáihni" "šilljocihci" ; #LIST ANIMAL-PLANT = # Plants that are rather animals (lingustically) SET ANIMAL = GEN-ANIMAL OR HUNT-ANIMAL OR BOAZU OR FISH OR PREDATOR OR BIRD ; SET ANIMATE = HUMAN OR ANIMAL ; #!! * Sets for things LIST TOOL = "áibmi" "ákšu" "bargobierggas" "baste" "bastevuogga" "báddi" "báddenrusttet" "beana" "bieggamillorusttet" "biebmu" "bierggas" (".*bissu"r) (".*bivddus"r) "bivttas" "boazonjuovvan#niibi" "bohtal" "borramuš" "buiku" "buođđu" "čáhci" "čála" "čogu" "čujonas" "čuoibmi" "datneárpu" "dáidda" "dálkkas" "dihtor" (".*mašiidna"r) "doarta" "dolgevuogga" "dolla" "dorte" "duodji" "duorgu" "ettetviidni" "fierbmi" "gáddenuohtti" "gáidánuohtti" "gáffal" "gáktesoadjá" "gazirdanniibi" "giehta" "giehtamihttu" "giehtaváđđu" "gievdni" "giikan" "goallunstoahku" "gohppu" "golgadat" "golle#bánno" "gurotgiehta" "hárpa" "jávre#vuogga" "joddu" "joddu-#buođđu" "kohppa" "kruvdnu" "láhkki" "láibi" "liidna" "liidnesihkaldat" "liššá" "luovosbeana" "luossa#vuogga" "luovos#fierbmi" "lyra" "maŋŋečanus" "mašiidna" "miehkki" "mihttu" "millo" "millu" (".*telefovdna"r) "mohtorsahá" "muorječoaggi" "muorravuogga" "nállu" "niibi" "njozon" "njuovvan#niibi" "oar-#juolgi" "oaggunstággu" "oaggunstávrá" "olgešgiehta" "olju" "riffal" "roahkkefierbmi" "ruhta" "ruvdnu" (".*sahá"r) "sáibma" "sáiti" "sálti" "seaila" "siibma" "sihkaldat" "sirpe" "skárbban" "skierat" "snáldu" (".*soabbi"r) "sabet" "soavvelvuogga" "spánnja" "speallanmašiidna" "spihkár" "stággu" "stávrá" "stivrran" "suohpan" "suorbma" "šlivgun#boksa" "váđđu" "veahkkemohtor" "veaikebaste" "vealgi" "viidni" "vuogga" "vuoiddas" "vuoigŋan#mašiidna" Sem/Tool Sem/Obj-el Sem/Obj-clo Sem/Obj-rope Sem/Tool-catch ; # Those could be further subdivided into: kitchen tools, working tools, hunting tools, fishing tools, writing tools... #LIST FISHING-TOOL = "buođđu" "fierbmi" "gáddenuohtti" "giehtaváđđu" "goallun#stoahku" "joddu" "joddu-#buođđu" "liidna" "luovos#fierbmi" "vuogga"; #LIST HUNTING-TOOL = "bissu" "HV-#bissu" "njuolla"; #LIST KITCHEN-TOOL = "baste" "gealva" "millo" "bánno"; #LIST WORKING-TOOL = "ákšu" "goaivu" "mohtorsahá" "nibi" "sirpe" ; #LIST COMMUNICATION-TOOL = "mobil#telefovdna" ; #LIST MACHINE = "bieggamillorusttet" "mašiidna" ; #LIST EATING-TOOL = "gáffal" ; LIST MUSIC-INSTRUMENT = "bássa" (".*čujonas"r) "gitárra" "hárpa" "lyra" "njálbmehárpa" "njurgganas" "piáno" "stráŋga" "urggut" Sem/Tool-music ; LIST WRITING-TOOL = "bliánta" "bleahkka" "dihtor" "krihtta" "liánta" "peanna" "peanná" "tušša" ; #LIST HANDICRAFT-TOOL = "áibmi" "datneárpu" "nálu" "suorbmagoahti" "vikšamuorra" ; # preliminary name for the set: LIST ABSTR-T = "bargobearráigeahčču" "bargodearvvašvuođa#bálvalus" "bearráigeahčču" "cummá" "dánsa" "dánsu" "dearvvašvuođageahčču" "doarjja" "eallin" "fápmu" "gásta" "geahčču" (".*goansta"r) "gullu" "heagga" "jahkebargu" "láhkavuođđudus" "mearka" "oahppu" "oaidninvuohki" "preassadoarjja" "prošeakta" "ruhtadoarjja" "sisabahkken" "soabadanproseassa" "sosialiserenproseassa" "suvli" "varra" "vuohki" ; LIST SINGLE-SOUND = "fonema" "jietna" "jietnadat" "loahppa#jietnadat" "vokála" ; # Can be part of a word LIST SOUND-SYSTEM = "básonšuokŋa" "čottajuoigan" "gohččun" "lávlunvuohki" "luohti" "musihkka" "riedja" "rohkos" Sem/Prod-audio ; LIST LANGUAGE = "jiddisch" (".*kielâ"r) (".*suopman"r) Sem/Lang ; SET SOUND = SINGLE-SOUND OR SOUND-SYSTEM OR LANGUAGE ; LIST SATNI = "adjektiiva" "advearba" "bárahisstávvalvearba" "boazosápmelaštearbma" "doaba" "kásushápmi" "kontráktavearba" "laktapartihkkal" "laktapartihkal" "namma" "partihkal" "partihkkal" "postposišuvdna" "preposišuvdna" (".*tearbma"r) "sátni" "sátnemátta" "substantiiva" "tearbma" "vearba" (".*sátni"r) (".*namma"r) ; ## tool for verbal activity LIST WORD-PARTS = "akseantamearka" "bustávva" "b-bustávva" "c-bustávva" "goallossáhcu" "gravismearka" "stávval" ; SET ABSTR-TOOL = SOUND OR ABSTR-T ; # Premilinary dividing of the set as a help for dimambiguating "gullat" vs. "gullát". #Those are typically comitative (instead of locative) if they go together with verbs from the LIST HUMAN-AGENT-V and probably also from INTELLECTUAL-ACTIVITY-V. The counterpart for locative is until now SITUATION, we might have to consider making a new list ABSTR-TOOL comprising SITUATION and other elements. #!! * Sets for qualities # - - - - - LIST COLOUR = "alit" "čáhppat" "fiskat" "fioleahtta" "ránis" "ruoná" "ruoksat" "runta" "ruškat" "sáhppat" "vielgat" "violeahtta"; #!! * Sets for things, not necessarily tools # - - - - - - - - - - - - - - - - LIST MATERIAL = "ávnnas" "báhkki" (".*náhkki"r) "gámas" "gihtta" "gusanáhkki" "materiála" "muorra" "náhkki" "ullu" "sávzzanáhkki" "silba" "stálli" ; LIST PLANT-PART = "lasta" "ruohtas" "upmol" ; # of plants etc. LIST SHOE = "čázet" "gállot" "gálssot" "gáma" (".*gáma"r) "goikket" "gummestevvel" (".*guohpá"r) (".*loabát"r) "njuorjjot" "nuhtat" "nuvttat" "nuvttot" "sabet" "sáppat" "sisttet" "skárri" "skuovva" "stevvel" "suohkku" (".*suohkku"r) ; # anything that will go on feet. IV-verbs like "vázzit" can take these as objekt. LIST BEDCLOTHES = "beaska" "gávnnit" "oađđádagat" "rátnu" "roavgu" "seaŋga"; # anything that can be used as bedclothing. IV-verbs like "oađđit" can take these as objekt. LIST CLOTHES = "avvi" "báidi" (".*báidi"r) "beaska" (".*bealjus"r) "bivttas" "boagán" (".*boagán"r) (".*buksa"r) (".*buser"r) (".*busir"r) (".*bivttas"r) "čalbmeláset" (".*čuhppa"r) "čuvla" "dorka" "fáhcca" (".*gahpir"r) "gákti" "gárvu" (".*gákti"r) "gistta" (".*hámet"r) (".*liidni"r) (".*luhkka"r) "rahpot" (".*readdju"r) (".*reddjo"r) "T-báidi" (".*váhcca"r) (".*váhttu"r) (".*vuolpu"r) Sem/Clth; LIST FOOD = (".*biebmu"r) (".*biergu"r) (".*borramuš"r) (".*muorji"r) "fuođar" (".*guolli"r) "gordni" (".*mális"r) (".*jáffu"r) "jokŋa" (".*láibi"r) "mális" "málli" "márfi" "niesti" "sarrit" "spelle" (".*gáhkku"r) Sem/Food ; # potential tool for political activity etc., potential place for other food, insects etc. LIST LIQUID = "bohccomielki" "bruvsa" "buolleviidni" "buolleviidna" "buollin#viidna" "buollánviidna" "buollánviidni" "čáhci" "čáhppesmuorjesákta" "čielgamielki" "deadja" "duolvačáhci" "gáffe" "gáiccamielki" "gearra" "girkoviidna" "girkoviidni" "goden" "gusamielki" "jugus" "juhkamuš" "kirkoviidna" "kirkoviidni" "mielki" "rihppaviidna" "rihppaviidni" "ruksesviidna" "ruksesviidni" "sarritsákta" "sáivačáhci" "sákta" "sávzzamielki" "suvramielki" "viidna" "viidni" "vilgesviidna" "vilgesviidni" "vuola" "vuolla" Sem/Drink ; LIST PLANT = "alášbađverássi" "alitdiehpperássi" "ávža" "báhpačehporaš" "beahci" "bastilislátnjá" "beahceguolbba" "beatnatnjuovččarássi" "biehtárguhkká" "biehtárrássi" "bievlaguolbba" "boallorássi" "biello#daŋas" "biellorássi" "cizáš#vuolpu" "duopma" "duottarbusságeahpil" "fiikkonmuorra" "fiskesrássi" "gálla" "gámasuoidni" "gáiski" "gáskálas" "gieddeguolbba" "gieddemáđir" "gollerássi" "guossa" "heasttagazzarássi" "horbmá" "jámešbátni" "jeagil" "juopmu" "lastamuorra" "lageš" "leaibi" "miestta" "muotkenjárgaguolbba" "niittoguolbba" "njálanjuovčča" "oaivejeagil" "oaksi" "rásseguolbba" "reatká" "sállja" "sieđga" "skáhpi" "skierri" "soahki" "suhpi" "uvlo#rássi" "vándádivga" "vilgesmáđir" "vuodjarássi" "vuovdeguolbba" Sem/Plant ; # Plants could be actors in fairytales (Alice) LIST FURNITURE = "áltár" "beavdi" "hildu" "ildu" "seaŋga" "skáhppe" "soffá" "stuollu" ; #!! * Sets for things such that people can be inside them: LIST SPACIOUS-VEHICLE = (".*fanas"r) (".*biila"r) "báska" "borjjasvanca" "bussa" (".*busse"r) "čáhcegirdi" "dámpa" "drošša" "drošše" "fievru" "gádjunhelikopter" "gávpotbussa" "geaksu" "girdi" "helikopter" "láivi" "minibussa" "mohtorfievru" "mohtorvanca" "njealjit" "njealljejuvllat" "ruvttobiila" (".*sáhttu"r) "skuvla#biila" "suhkkivanca" "tákse" "táksi" "toga" "traktor" "tráktor" "vanas" "vanca"; #!! * Sets for things such that people cannot be inside them: LIST SMALL-VEHICLE = "ásen" "beana" "fievrošibit" "heargi" "heasta" (".*sáhttu"r) (".*sihkkel"r) "mohtorgielká" "mopeda" "njealljejuvllat" "skohter" "spárka" "skuter" "sykkel" "njealjejuvlageassi" "vuoksá" ; SET VEHICLE = SPACIOUS-VEHICLE OR SMALL-VEHICLE OR Sem/Veh ; LIST TEXT = "áppes" (".*listu"r) (".*čálus"r) (".*girji"r) (".*-girji"r) (".*gažaldat"r) (".*aviisa"r) (".*áviisa"r) (".*bábir"r) (".*logahallan"r) "bargobihttá" (".*prográmma"r) (".*lávlla"r) (".*bláđđi"r) (".*mearrádus"r) "bušeahttapoasta" (".*čála"r) (".*cealkámuš"r) "čuovus" (".*teaksta"r) (".*dieđáhus"r) (".*journála"r) "dokumeanta" (".*girje"r) "e-poasta" (".*eksamen"r) "eksamenbihttá" "fáddásiidu" "fáksa" "gáldu" "gullugovva" "journála#čállin" "journáladiehtu" "kárta" "lasta" (".*láhka"r) "láđđi" "leaksu" "mátkemuitalus" "mielddus" "neahttasiidu" "novealla" (".*raporta"r) (".*reive"r) "riektedieđa" "romána" "ruovttubargu" "ruovttusiidu" (".*konvenšuvdna"r) "sárdni" "sitáhtta" "statistihkka" "telegrámma" "váidda" Sem/Txt ; # A potential place (locative?) for sth. written. # Maybe one should differentiate between written and spoken texts LIST ABSTR-TEXT = "áddejupmi" (".*plána"r) (".*mearrádus"r) (".*evttohus"r) (".*njuolggadus"r) (".*ortnet"r) (".*árvalus"r) (".*cealkámuš"r) "cuvccas" "doaibmabidju" "eaktu" "eanačujuhus" "gažaldat" "gáhtteneaktu" "gáldokoda" "geasku" "giellagažaldat" "jearaldat" "lappekodisilla" "láhkaásahus" "luođaleaktu" (".*mearrádus"r) "máinnas" "muitalus" "resolušuvdna" "sáme#kodisilla" (".*soahpamuš"r) ; # A potential place (locative?) for sth. written, spoken or abstract activity #!! * Part-whole sets for human LIST BODY = "alimat" "aski" "ámadadju" "bahta" "bahtačalbmi" "bahtaráigi" "bavssa" "bállosuotna" "bátni" "beađbelađas" "bealgi" "beallji" "bierggas" "biežadákti" "billu" "buđđá" "bullječalbmi" "čalbmečiehka" "čalbmedeahkki" "čalbmegolláš" "čalbmegulbmi" "čalbmeguolga" "čalbmeluopma" "čalbmi" "čatnangođđu" "čeabet" "čelččen" "čeŋkkeš" "čibbeskálžu" "čibbi" "čižžebátni" "čižži" "čielgeađa" "čielgedákti" "čielgi" "čoalli" "čoamohas" "čoarbbealdeahkki" "čoarbbeallađas" "čoarbbealli" "čoavji" "čorbma" "čorbmaoassi" "čorbmaváimmus" "čorbmavuođđu" "čotta" "čuožžamasdeahkki" "čurti" "čuvdi" "dábba" "dáđvi" "dáktegođus" "dákti" "dávdi" "deahkkegođus" "deahkki" "erttet" "erttetdeahkki" "gahpárus" "gahperus" "ganjalčalbmi" "gardnjil" "gaskasuorbma" "gassačoalli" "gassaváhkká" "gáddu" "gáibi" "gállu" "gánis" "gátnis" "geađđi" "geahpis" "giegir" "giehta" "giehtadeahkki" "giehtagávva" "giehtaláhpi" "giehtaramas" "giehtaruohtas" "giehtasealgi" "giehtaváibmu" "giehtaváimmus" "gilga" "gipsajuolgi" "goapmirváimmus" "goaŧŧočotta" "goaŧŧu" "goikedákti" "gorut" "gullu" "guoggomas" "guoggomasráksá" "gurotgiehta" "hárdu" "heaggaroasmmoheapmi" "jarri" "juolgebealgi" "juolgečelččen" "juolgedeahkki" "juolgegávva" "juolgelađas" "juolgeláhpi" "juolgemátta" "juolgesuorbma" "juolgevuođđu" "juolgi" "lađas" "láhpelađas" "manin" "maŋŋebuoidi" "mánágoahtečotta" "mánágoahti" "mielganjunni" "monimuš" "monin" "monnejođas" "monneráksá" "morčesuotna" "morči" "muohtu" "náhpi" "nealgečoavji" "niehkki" "nierra" "niskegohpi" "niski" "njálbmi" "njiehcehas" "njunni" "njuovčča" "oaiveassi" "oaivečohkka" "oaivi" "oalgedeahkki" "oalgenorasdeahkki" "oalgenorasváhkká" "oalgi" "oalul" "obbalággá" "orbbeš" "raddi" "rápma" "rumaš" "rumaš#golggus" "rumašlahttu" "rumašnjalbi" "sáhppesuvri" "rumašlahttu" "rumašnjalbi" "salla" "sáhppesuvri" "siidu" "siskkitbeallji" "sotkenoalli" "spirralat" "suolbmudanoalli" "suorbma" "suorbmageahči" "šušmi" "váhkkádeahkki" "váibmu" "vuohččecuozza" "vuoivvas" "vuokta" "vuolit" "vuorggu" Sem/Body "garragiehta" ; LIST WEATHER-ENTITY = "balva" "arvi" "muohta" Sem/Wthr ; #!! * Sets for places LIST BUILDING = "áiti" "ámmátskuvla" "biebmorámbuvri" "barta" "badjedállu" "boasta" "buohcciidsiida" "buohcceviessu" "buvda" "buvri" "dállu" "dálveskuvla" "dálveviessu" "eanandoalloallaskuvla" "fáŋgaviessu" "fiervábuvri" "geaidnogievkkan" "geardeviessu" "geasse#buvri" "goahti" "gávpi" "gieldda#skuvla" "girku" "hotealla" "internáhttaskuvla" "inšenevraallaskuvla" "kaféa" "krámbuvda" "kulturskuvla" "láđđu" "láhtu" "lávvu" "lonuhusgávpi" "mánáidskuvla" "mearra#buvri" "mearraskuvla" "musihkka#allaskuvla" "návet" "návetgoahti" "návsti" "návstu" "nuoraidskuvla" "oktasašbarta" "orrunviessu" "poasta" "priváhtaskuvla" "ráidoviessu" "rámbuvri" "rámbuvra" "rásseláđđu" "riika#skuvla" "riika#buohcceviessu" "sámeskuvla" "skuvla" "stálla" "stálle" "stállja" "stohpu" "synagoga" "šloahtta" "tempel" "tuolloviessu" "universiteahtta" "viessu" "visti" Sem/Build ; LIST GENERAL-PLACE = "albmi" "almmiravda" "almmiriika" "areála" "atnueana" (".*guovlu"r) "ássanbáiki" "badjegeardi" "badjeeana" "báikegoddi" "báiki" "báktehárji" "bealdu" "biegga#báiki" "biras" "boazoguohtoneana" "buođđosadji" "čakčaeana" "čakčaeana" "čakča#báiki" "čakčaorohat" "čiegus" "čoahkkebáiki" "dálvebáiki" "dálveeana" "dálveguohtoneana" "dálveorohat" "davviriika" "davvisiida" "dánssa#báiki" "diggebáiki" "dimbbar#čuohppan#sadji" "dollagáddi" "duiska#eana" "eanandoallo-#eana" "eanandoalloeana" "earre#sadji" "fanasláttasadji" "fágabiras" "gádde#báiki" "gádde#ravda" "gávpebáiki" "gávpemárkan" "gávpot" "gávpotpoarta" "geaidnoguorra" "geaidnoravda" "geassebáiki" "geasseeana" "geasseguohtoneana" "geasseorohat" "geassesadji" "gilli" "giddagas#báiki" "giđđabáiki" "gieddeeana" "gilvvagárdi" "gilvvohallanbáiki" "girkogárdi" "goahtesadji" "goikeeana" "guoddinseaŋga" "guollebáiki" "guollebivdosadji" "guohtoneana" "guohtuneana" "guottetbáiki" "hámman" "hávdeeana" "helvet" "jeaggeeana" "jeagelguohtuneana" "jienastanbáiki" "kálka#eana" "kontineanta" "lassieana" "láigoeana" "luome#eana" "luossabáiki" "luonddubiras" "máilbme#čiehka" "máilbmi" "márkan" "meahcceeana" "meahccegilli" "njáskan#báiki" "njunušsadji" "nuortaeana" "oahppobáiki" "oaivegállobáiki" "oktasašeana" "oktasašorohat" "olgobáiki" "olgoriika" "orohat" "orrunbáiki" "priváhtaeana" "rasttidanbáiki" "ránnáriika" "riddo#eana" "riika" "ruoktu" "ruovdemáđidja" "ruovttueana" "sadji" "sáidebáiki" "sámieana" "sámeeana" "sámevearroeana" "sallju" "siida" "siseana" "skoaltabáiki" "skuvlabiras" (".*šillju"r) "stáhtaeana" "stáhtasadji" "TV-šearbma" "váhneneana" "várdobáiki" "vearroeana" "viessosadji" "viesttarbađaeana" "virgebáiki" "vuoiŋŋastanbáiki" "vuopmeeana" ; LIST NATURE-PLACE = "almennet" "ávži" "bákti" "beahcevuovdi" "borri" "buollán#ávži" "coagis" "čázádat" "čolpi" "darfejeaggi" "dearbmi" "duottarjávri" "duottaroassi" "eatnu" "fielbmá" "fiervá" "gáddi" "gáisá" "gáisi" "gárggu" "gárgu" "gieddi" "gieva#jeaggi" "gohpi" "gohppi" "gorži" "guolbba" "gurra" "jávri" "jávregáddi" "jeaggi" "jiehkki" "johka" "johka#gaska" "johkagáddi" "johkaleahki" "johkanjálbmi" "láddu" "láttu" "latnja" "lavdnjejeaggi" "leahki" "lokta" "luohkká" "luokta" "luondu" "luoppal" "luossajohka" "meahccegieddi" "mearra" "mielli" "mohkki" "muotki" "njárga" "njunni" "oaivi" "oalgejohka" "oalgi" "orda" "orrit" "rádja#čázádat" "reašši" "riddogáddi" "riddu" "riidi" "ruovttugieddi" "soahkevuovdi" "stealli" "várrevielti" "várri" "vearroduottar" "vielti" "vuohppi" "vuotnabahta" "vuotnagáddi" ; #LIST ELEMENT = "áibmu" "čáhci" "dolla" ; ## (probably often place) They are often tools - they are not probably Pl Loc. LIST SETTLEMENT-PLACE = "ássanguovlu" "duottar" "eana" "eanaguovlu" "gáddi" "geassesiida" "Gennesaretjávregáddi" "gilli" "guovlu" "mátkeguovlu" "meahcci" "mearragáddi" "njárga" "riddu" "sámisiida" "siseana" "siseatnansiida" "sisvuotna" "suolu" (".*jávregáddi"r) "vággi" "vuotna" "vuotnabahta" "vuotnagáddi" "vuotnaguovlu" "vuovdi" ; SET GEOGRAPHICAL-PLACE = NATURE-PLACE OR SETTLEMENT-PLACE ; LIST GEN-POLITICAL-PLACE = "gávpot" "gilli" (".*suohkan"r) "fylka" "orohat" "rádji" "riika" "riikkarádji" "ruovttugávpot" "sámeeana" "Sámeeana" "siseatnangilli" "stáhta" "válgabiire" "vuotnagávpot" ; ## can also function as an actor LIST FYLKA = "Finnmárku" "Finnmarku" "Romsa" "Nordlánda" "Lulli-Trøndelag" "Davvi-Trøndelag" "Hedmárku" "Akershus" "Buskerud" "Vestfold" "Østfold" "Aust-Agder" "Vest-Agder" "Rogalánda" "Hordalánda" "Opplánda" "Fjordane" "Romsdal" "Telemark" ; LIST NORGA = "Dánmárku-#Norga" "Danmárku-#Norga" "Davvinorga" "Davvi-Norga" "Gaska-Norga" "Norga" "norga" "norggabealli" "Norga-#Ruoŧŧa" ; LIST NATION-NOT-NORGA = "Columbia" "davvi#ruoŧŧa" "Duiska" "Frankriika" "Guatemala" "Israel" "Kanada" "Láhten-Amerihká" "naššuvdna" "riika" "Ruošša" "Ruoŧŧa" "Sápmi" "sápmi" "Skandinávia" "stáhta" "Suopma" "Suopma-#Ruošša" ; SET NATION = NATION-NOT-NORGA OR NORGA ; SET POLITICAL-PLACE = NATION OR GEN-POLITICAL-PLACE OR FYLKA OR (".*gielda"r) ; # Can be an actor # This set is important for distiguishing "vuodjit" and "vuodjat", so there shouldn`t be words which can be combined with "vuodjat": LIST CONCRETE-ROUTE = (".*máđidja"r) (".*máđii"r) (".*bálggis"r) (".*luodda"r) (".*geaidnu"r) (".*gáhtta"r) (".*guorra"r) (".*láhttu"r) (".*ráigi"r) "ráidu" "spáiddarráidu" ; # and others! LIST ABSTR-ROUTE = "gaska" "mátki" "miila" "mohkki" "tuvra" ; SET ROUTE = CONCRETE-ROUTE OR ABSTR-ROUTE ; LIST WATER = "ája" "áhpi" "álddis" "basseaŋŋa" "čáhci" "cázádat" "Deanučáhcadat" "Deanucázádat" "eatnu" "fielbmá" "jávri" "johka" "luokta" "mearra" "sálteája" "vuodjanálddis" "vuojadanálddis" "vuotna" ; LIST GOAHTI-PLACE = "árran" "boaššu" "loaidu" "reahpenráigi" "soggi"; LIST ROOM = "bargomárkankantuvra" "bártniidhivsset" "biergodiehtojuohkinkantuvra" "boazodoallokantuvra" "čájáhuslatnja" "ealáhuskantuvra" "eamiálbmotkantuvra" "eanajuohkinkantuvra" "eananvuovdinkantuvra" "eanavuovdinkantuvra" "feaskkir" "fylkkaeanadoallokantuvra" "gámmár" "gámmir" "garáša" "gievkkan" "guovllukantuvra" "hivsset" "informašuvdnakantuvra" "kantuvra" "klássalatnja" "leansmánnekantuvra" "lášmmohallansále" "lášmmohallansálla" "livnnetkantuvra" "lokta" "luohkkálatnja" "molssodanlatnja" "nieiddaidhivsset" "nohkkanlatnja" "oađđenlatnja" "oađđinlatnja" "oahpaheaddjilatnja" "sallju" "skuvlalatnja" "sosiálkantuvra" "stohpu" "studio" "šillju" Sem/Build-part ; SET PLACE = GEOGRAPHICAL-PLACE OR POLITICAL-PLACE OR GENERAL-PLACE OR ROUTE OR BUILDING OR ROOM OR GOAHTI-PLACE OR Sem/Plc ; LIST MAIN-ORGANIZATION = (Prop Sem/Org) "alimusriekti" "ámtadiggi" (".*ásahus"r) "bargokantuvra" "báhpaskuvla" "bálvalandoaibma" "bearráigeahččanorgána" (".*bellodat"r) "buohccestohpu" "buohcceviessu" "buohcciidsiida" "dearvvašvuođafitnodat" (".*departemeanta"r) "dearvvašvuođadutkanguovddáš" "diggi" (".*direktoráhta"r) "duopmostuollu" "eananjuohkindiggi" "eiseváldi" "Finnmárkokommišuvdna" "firbmá" "fitnodat" "fylka" "fylkkagielda" "geahččo#doaibma" "geahččoeiseváldi" "gelbbolašvuođaguovddáš" "giddagas" "gieldda#diggi" "giellaguovddáš" "giellakantuvra" "giellaráđđi" "girjerájus" "girku" "girkoráđđi" "gozihankomitea" "guovddášeiseváldi" "guovllubuohcceviessu" "hálddašanorgána" "hállehus" "dearvvašvuođaguovddáš" "fylkkadiggi" "institušuvdna" "justiskomitea" "klinihkka" "komitea" "komišuvdna" (".*lávdegoddi"r) (".*listu"r) "mánáidgárdi" "media" "meieriija" "militeara" "musea" "našunála#diggi" "oahpahusdoaibma" "oahpahuskantuvra" (".*organisašuvdna"r) "orgána" "parlameanta" "psykiatriijabuohcceviessu" "preassa" "ráđđehus" (".*ráđđi"r) "Sámediggi" "sámediggi" "sámeinstitušuvdna" "sámekomitea" "sámemišuvdna" "sámemusea" "sámesiida" "searvegoddi" (".*searvi"r) "servodat" "sierraduopmostuollu" (".*skuvla"r) "skuvlakantuvra" "stáhta" "stuorradiggi" "suodjalankomitea" "suohkan" (".*stivra"r) "synagoga" "universiteahtta" "universitehta" "universitehtabuohcceviessu" "dearvvašvuođastašuvdna" "gielda" "riddogielda" "ruovttugielda" "sámegielda" "vuotnagielda" ; LIST DEPARTMENT = "doaibmaguovddáš" "fakultehta" "etáhtta" (".*guovddáš"r) "hálddahus" "instituhtta" "kantuvra" "giellakantuvra" "mearridanorgána" (".*ovttadat"r) (".*ossodat"r) ; SET ORGANIZATION = DEPARTMENT OR MAIN-ORGANIZATION OR Sem/Org ; #Not sure about Sem/Org #!! * Sets that can both be buildings/places and represent humans LIST INSTITUTION = "geahččoortnet" "guovddáš" "instituhtta" "kulturráđđi" "searvegodderáđđi" ; # the previous items can both represent abstract processes and humans LIST MEDIA = "media" "oahpahus#rádio" "rádio" "televišuvdna" "TV" ; #SYMB-INSTITUTION = "njuolggadus" "vuoigatvuohta" "láhka" "ortnet" "čoahkkinortnet" ; # Those cannot be buildings, but 'act' , 'say' things for example.. # Two aspects: Place and institution: # and a couple of other words that do not really have to do with that # suits "vázzit" + Acc LIST EDUCATION = (".*skuvla"r) "skuvla" (".*oahppu"r) "artiumkursa" "badjedássi" "báhpaskuvla" "boazodoallofága" "boazodoallosuorgi" "dásseárvofága" "duodjekursa" "fága" "gaskadássi" "giellafága" "giellagursa" "gursa" "joatkkakursa" "joatkkaoahppu" "kursa" "luohkká" "luonddufága" "mánáidskuvla" "musihkkadiibmu" "musihkkasuorgi" "oahppofálaldat" "oahppoinstitušuvdna" "oahppoásahus" "oahppodássi" "sámegielfága" "sámegiel#gaskafága" "seminára" "skuvla" "stáhtainternáhtta" "stáhtainternáhta" "stuorraskuvla" "universiteahtta" "universitehta" "vuolledássi" Sem/Edu ; # suits to LANGUAGE Gen LIST LESSON = "álgogursa" "dáiddaoahpahus" "gaskafága" "gealbu" "gelbbolašvuohta" "giellaovdáneapmi" "fálaldat" "joatkkafáddá" "joatkkagursa" "lávdaoahppofálaldat" "lohkanbájioahppu" "máhttu" "musihkkadiibmu" "oahppa" "oahppofálaldat" "oahpahus" "váldofága" "vuođđofága" ; LIST OTHER-INDUSTRY = (".*ealáhus"r) "biedjo#bivdu" "bivdu" "boazodoallu" "Deanubivdu" "duodji" "ealáhusdoaibma" "eanandoallu" "fuođđobivdu" "geasse#guollebivdu" "giđđa#guollebivdu" "goddebivdu" "guollebivdu" "industriija" "johka#luossabivdu" "lassiealáhus" "luossabivdu" "oapmedoallu" "riektepolitihkka" "rievssatbivdu" "ruvkedoaibma" "sáivaguollebivdu" "sáivabivdu" "sosiálapolitihkka" "šákša#dorske#bivdu" "sámeduodji" "smávva#bivdu" "šibitdoallu" ; # Not related to certain political verbs # Duomma:lea LIST POLITICAL-INDUSTRY = (".*politihkka"r) ; # Related to certain political verbs # Duomma:lea SET INDUSTRY = POLITICAL-INDUSTRY OR OTHER-INDUSTRY ; LIST RIEKTEDILLI = "bajithearrávuohta" "bálvalusfálaldat" "čearddalašvuohta" "diggegirji" "dilálašvuohta" "ealáhusvuođđu" "eallindiliváttisvuohta" "eanajuohkinsuohkan" "eanadoallobuvttadeapmi" "eanavuovdinkantuvra" "hálddašeapmi" "kultuvra" "matrihkal" "meahcceriggodat" "opmodat" "rádjemearka" "rádji" "rádjá" "resursageavaheapmi" "riektedilli" "riekteáddejupmi" "riddomearraguovlu" "sierraortnet" "stáhtaeana" "suodjalanguovlu" "váldofierpmádat" "vearronjuolggadus" "vuoigatvuođadilálašvuohta" (".*vuoigatvuohta"r) "vuovdeatnu" "vuovde#njuolggadus" "suverenitehta" "kulturdoarjja" ; # FYLKA in front of the set is usually in Gen. LIST STAHTA-GEN = "IT-#doaibmaplána" "almennet" "bargiidgiehtagirji" "boazodoallohálddahus" "bálvalus" "dearvvašvuođageahčču" "dearvvašvuođaiskkadeapmi" "dearvvašvuođa#gozáhus" "doaibma" "doaibmaplána" "doarjja" "doarjjavuogádat" "dássi" "eaiggáduššanvuoigatvuohta" "eaiggátgáibádus" "eana" "eiseváldi" "gaskadilleortnetdoarjja" "geahččoortnet" "geatnegasvuohta" "geavat" "gáibádus" "háldu" "joatkkaskuvla" "kulturráđđi" "mearrabodni" "oahppodoaibma" "oaidnu" "oaivil" "orgána" "ovddasteaddji" "peršonalgiehtagirji" "ruhta" "sosiálapolitihkka" "spesialistadearvvašvuođabálvalus" "tariffašiehtadus" "vuostebealli" "áddejupmi" "ámmátolmmoš" "ásahus" ("jávri" Pl) "oassálastin" ("vuovdi" Pl) "áŋgiruššan" ; # "stáhta" in front of the set, is usually Gen. LIST SAMEDIGGI-GEN = "autoritehta" "áirras" "árvokommišuvdnalahttu" "ásaheapmi" "bargu" "bušeahtta" "bušeahttamearrádus" "bušeahttavuogádat" "čielggadeapmi" "čilgehus" "čoahkkin" "čoahkkinortnet" "dievasčoahkkin" "doaibma" "doaimmahat" "ealáhusfoanda" "ekonomiijahálddašeapmi" "ekonomiijastivret" "hálddašanapparáhtta" "jahkedieđáhus" "joavku" "kulturviessobušeahtta" "lahttu" "mearrádus" "njuolggadus" "nuoraidkonferánsa" "oaidnu" "oassálastin" "ollesáigepolitihkkár" "opposišuvdna" "ovttasbargoaktøra" "politihkkár" "rehketdoallu" "sadji" "ságajođiheaddji" "šiehtadusmálle" "ulbmil" "váldoášši" "váldohálddahus" ; SET ACTOR = ANIMATE OR INSTITUTION OR ORGANIZATION ; # Should EVENT be part of this set? # To be used in habitative-sentences: SET HAB-ACTOR = ACTOR OR HUMAN-GROUP OR EDUCATION OR PEOPLE-NUM OR ("gii") OR Pers OR ("eará") OR ("iežá") OR ("buohkat") OR ("gaikkat") OR ("juohkehaš") OR ("goappašagat") OR ("soames") OR ("oktage") OR Sem/Hum - SAPMI ; SET HAB-ACTOR-NOT-HUMAN = INSTITUTION OR ORGANIZATION OR INDUSTRY OR EDUCATION ; LIST STATE = "bahávuohta" "dearvvasvuohta" "gaskavuohta" "mielladearvvašvuohta" "ráfi" "váivi" "veahkki" Sem/State; LIST OTHER-ABSTR-ENTITY = "ášši" (".*prošeakta"r) (".*plána"r) "hehttehus" "váttisvuohta" ; # can represent a concrete entity LIST MONEY = "ánsu" "árvu" (".*bálká"r) (".*bušeahtta"r) (".*buhtadus"r) "dienas" "divat" (".*doarjja"r) (".*gollu"r) "haddi" "juolludeapmi" "juolludus" ("liigudit" Der/NomAct) "máksu" "reantu" (".*ruhta"r) "sáhkku" "sisaboahtu" "tienas" "vealgi" "vearru" "vuoitu" Sem/Money ; # Ambiguous with respect to concreteness, either the symbolic amount or the concrete coins and bills SET ABSTR-ENTITY = MONEY OR STATE OR OTHER-ABSTR-ENTITY ; LIST GEN-CONCEPT = "anistupmi" "álgu" "áŋgirvuohta" "áigumuš" "árbevierru" "ávžžuhus" "ballu" "bálvaleapmi" "bálvaluskvaliteahtta" "bargomálle" "boađus" "dárbu" "dássi" "doaibma" "duođaštangeatnegasvuohta" "duogáš" "eaiggátvuohta" "eallinvuohki" "erohus" "evttohus" "fádda" "friddjavuohta" "fuolalašvuohta" "gaskamearri" "gaskaoapmi" "geargatvuohta" "geatnegasvuohta" "gelbbolašvuohta" "gudnejahttin" "gudni" "hállu" "hástalus" "isitvuohta" "konflikta" "kontákta" "kulturduogáš" "kulturmáhttu" "kvaliteahtta" "loahppa" "loatnaetymologiija" "lohpi" "máhttu" "máŋggabealatvuohta" "miella" "mihttomearri" "molssaeaktu" "muitu" "oamedovdu" "oktavuohta" "olahahttivuohta" "ovdamearka" "ovddasvástádus" "ovttadássásašvuohta" "perspektiiva" "ráffi" "ráfi" "ráhkisvuohta" "rámma" "riekteprinsihppa" "rolla" "sámegielmáhttu" "sámekultuvra" "sihkkarastinstrategiija" "strategiija" "šiehtadallanfáddá" "symbolasystema" "ulbmil" "ustitvuohta" "vanhurskkisvuohta" "váibmu" "váikkuhanfápmu" "váikkuhus" "váldosivva" "vásáhusduogáš" "vearrivuohta" "virgelohpi" "vuordámuš" (".*vuoigatvuohta"r) ; # very abstract # Adding words to this set, consider if they suit to the SG-WORD-set as well. LIST EMOTION = "gierisvuohta" "moraš" "ráhkisvuohta" "vašši" Sem/Perc-emo ; LIST STRUCTURE = "álgu" "loahppa" "struktuvra" "maŋŋegeahči" "lasáhus" "loahppageahči" "álgogeahči" "álgooassi" "sisdoallu" "veršuvdna" ; LIST PROPERTY = "burrodat" "fastivuohta" "hedjodat" "allodat" "gassodat" "kvaliteahtta" "sturrodat" "guhkkodat" "govdodat" "hápmi" "ivdni" "fearga" "dovdomearka" "iešvuohta" "viidodat" ; LIST IDEOLOGY = "buddhisma" "geahččanguovlu" "kommunisma" "oaidninčiehka" "osku" "sosial#darwinisma" ; SET CONCEPT = GEN-CONCEPT OR STRUCTURE OR PROPERTY OR IDEOLOGY ; LIST ACTIVITY = "aktivitehta" "báikenammadutkamuš" "boazodoallodutkamuš" "čađaheapmi" "dearvvašvuođadutkan" "eallinbirasdutkamuš" "fuolaheapmi" "geahčastat" "gilidutkamuš" "guorahallan" "heahtebargu" "loatnadutkamuš" (".*lodden"r) "lodden" "mátki" "návetbargu" "sámedutkamuš" "sisafárren" "substráhtadutkamuš" "šiehtadallan" ; # semantically comparable to Actio forms + lexicalized Der/NomAct forms. # probably change of state in the course of time LIST PROCESS = (".*proseassa"r) ; # Reminds of time sets LIST TOPIC = "areálaášši" "áideášši" "boazodoalloášši" (".*-#ášši"r) "buhtadusášši" "bušeahttagáržžidanášši" "čázádathuksenášši" "čiekŋudanfáddá" "čoahkkin#ášši" "diggeášši" "doarjja#juohkin#ášši" "eallinášši" "eanamihtádusášši" "eaŋkalášši" "eananoastinášši" "giellaášši" "girkoášši" "gudnerihkkun#ášši" "guolle#ášši" "guovlogáhttenášši" "hálddašanášši" "huksenášši" "individuála#ášši" "juogadanášši" "konsešuvdnaášši" "lassiášši" "luonddugáhttenášši" "meroštanášši" "mudden#ášši" "namma#logahallan#ášši" "nággoášši" "rádjaášši" "ráfáiduhttinášši" "rávdnje#huksenášši" "riidoášši" "sámeášši" "sisbuksa#ášši" "suohkanstivrraášši" "plánaášši" "riekteášši" "sámeášši" "suopman#ášši" "váiddaášši" "váidinášši" "váldoášši" "vearroduottarášši" "vuoigatvuođaášši" ; SET ABSTRACT = ABSTR-ENTITY OR CONCEPT OR ACTIVITY ; LIST DILLI = (".*dilli"r) ; # Likely to be locative in most contexts LIST WEATHER-SITUATION = "beaivvádat" "bievla" "buolaš" "dálki" "dálkedilálašvuohta" "fiertu" "goalki" "siivu" "jođádat" "liekkas" "linádat" "oppas" "riđđu" "muohtti" "ilbmi" "balva" "čuoika" "čoaskin" "biegga" "nuorttadat" "davádat" "oarjjádat" "luládat" "orjješbiegga" "nuortabiegga" "obbadálki" "balvadálki" "balva#ilbmi" "arvi" "savda" "savda#arvi" "liehmu" "láfubiegga" "baján" "johtti" "gállu" "jiella" "hieibma" "šlahtti" "seaŋáš" "borga" "guoldu" "dobadat" "dulvi" "moarri" "geardni" "cuoŋu" "jealahas" "jalahas" "geasádat" "dálvvádat" "jáldu" "lievhnu" "galmma" "guostta" "čođđolat" "čođđálat" "sealádat" "šearádat" "bálgu" "bálggádat" Sem/Wthr ; SET SITUATION = DILLI OR WEATHER-SITUATION ; SET ACTOR-ROLE = HUMAN OR ORGANIZATION OR POLITICAL-PLACE OR EDUCATION ; # Institution: Restricting possible actor subjects. LIST EVENT-TOOL-ACTIVITY = Der/NomAct "addin" "dearvvašvuođaiskkadeapmi" "goddin" "hárjehallan" "jápmin" "ráđđádallan" "šiehtadallan" "vázzin" ; LIST EVENT = (".*čoahkkin"r) "čoakkalmas" (".*márkan"r) "boazodoallošiehtadallan" "cup" "čuoigan#cup" "deaivvadeapmi" "doallu" "feasta" (".*festivála"r) "heajat" (".*gilvu"r) "konferánsa" "konsearta" "kursa" "máilmmesoahti" "mátki" "mearridanproseassa" "proseassa" "ruhkos" "soahti" (".*válga"r) "vuosttaščájálmas" Sem/Event ; #XXX bad name, too general SET ABSTR-PLACE = ORGANIZATION OR INSTITUTION OR EVENT OR EDUCATION OR INDUSTRY OR SITUATION ; LIST ILLNESS = "albmasuoigi" "allergiija" "anemiija" "báhti" "bátnevárka" "bátnevearka" "bárku" "bearri" "boahkku" "buohcu" "buohcuvuohta" "buollán" "buozalmas" "čoavjebávččas" "čoavjebonjahat" (".*dávda"r) "eksema" (".*feber"r) "gárrenávnnas" "gárrenávnnasváttisvuohta" "gárrendilli" "influeansa" "juhkanvuohta" "leasmi" "mánodávddat" "nuorvu" "oaivvesvuohta" "ráŋka" "ruodnu" "skihpa" "suohtta" "varrasonahat" (".*váddu"r) (".*vihki"r) (".*vuolši"r) "vuorri" Sem/State-sick ; # LIST ANIMAL-ILLNESS = "luossadávda" "vuorri" ; #!! * Sets denoting relations LIST OASSI = "gonagasoassi" "riika#oassi" "riikkaoassi" "oassi" "teakstaoassi" "váldooassi" ; # Might be useful for partitive constructions. # Try to make a set of nouns wich not will be Gen in a AccGen string. LIST HEADOFPARTS = "eanetlohku" "unnitlohku" "mearri" "nissonoassi" "oassi" "váldooassi" "bealli" "guhtemuš" "goappašat" "proseanta" "%" Sem/Part ; # This may be a better partitive set. #!! !Miscellaneous sets # ------------------ LIST Px = PxSg1 PxSg2 PxSg3 PxDu1 PxDu2 PxDu3 PxPl1 PxPl2 PxPl3 ; SET N-NOPX = N-NOPXLIST OR LAHKA OR EDUCATION ; LIST GASKAL = "gaskal" "gaskkal" "gaskii" "gaskka" "gaskkas" ; # p-positions that like coordination LIST TIME-PP = "badjel" "čađa" "earret" "gaskkal" "guovddáš" "maŋŋel" "maŋŋil" "maŋŋá" "miehtá" "ovdal" ; SET NUM = Num - OKTA ; # this set does not contain ordinals, I am not sure if that is necessary. SET NOT-NUM = WORD - Num ; LIST MANGA = "máŋga" "galle" ; # Not referred to by any rule. SET CARDINALS = Num - Ord - MANGA ; SET NOT-CC = WORD - CC ; SET NOT-PCLE = WORD - Pcle ; LIST COMPAR = ("dávji" A Comp) "eanet" "earalágan" "eará" "iežá" "earret" "seammás" "seammalágan" "seamma_láhkái" ; # These combine with "go" Pcle, but COMPAR stands for 'comparison' rather than # 'comparative'. LIST CONTRA = "muhto" ; # In lean muitalan, muhto dál muitalan. LIST PROSEANTA = "proseanta" "%" ; SET REAL-CLB = CLB - COMMA ; SET NOT-INITIAL-CC = WORD - INITIAL - CC ; #!! !Border sets and their complements # --------------------------------- SET CP = (Pron Interr) OR (Pron Rel) OR MO ; LIST BOUNDARYSYMBOLS = "\;" ":" "-" "–" ; # This set if for disambiguating rules after mapping @CVP and @CNP to all CS and CC readings, therefore we cannot have @CVP in the set SET S-BOUNDARY-NOT-CVP = CP OR BOUNDARYSYMBOLS OR ("muhto") OR ("de" Adv) OR (Neg Sup) ; SET S-BOUNDARY = CP OR BOUNDARYSYMBOLS OR ("muhto") OR ("de" Adv) OR (Neg Sup) OR (@CVP) OR ("vel" Adv Qst) ; # does not include CS, because of "go" in questions, before it is disambugated. # includes CP # this one includes @CVP, the conjunction which actually connects two sentences (each with a finite verb) to each other, # and not @CNP, which coordinates internal NP-/AdvP-/AP ... coordination # To be used only AFTER the disambiguation of @CVP and @CNP taking place in the chapter right before "Disambiguating pronouns" SET BOC = S-BOUNDARY OR BOS ; SET BOC-PUNCT = BOC - ("-") - ("–") ; SET EOC = S-BOUNDARY OR EOS ; SET NP-BOUNDARY = BOS OR EOS OR REAL-CLB OR VFIN OR Inf OR (Actio Ess) OR ConNeg OR VGen OR Sup OR PPRON-NOT-GEN OR Recipr OR Po OR Pr OR Pcle OR ("jed") OR Interj OR CS OR CP OR @CVP ; SET APP-BOUNDARY = REAL-CLB OR VFIN OR Inf OR (Actio Ess) OR ConNeg OR VGen OR Sup OR Recipr OR Po OR Pr OR Pcle OR Interj OR CS OR CP ; # A special barrier used with mapping of appositions. # This set contains FMAINV with @, which means that it functions for all kind of mainverbs after the verb-mapping rules SET SV-BOUNDARY = S-BOUNDARY OR Inf - AUX OR Sup OR FMAINV ; # VFIN-NOT-AUX ; # should be MAIN-V linked to VFIN-aux to the left. (cg-3) # This set is ment to use in rules for disambiguating due to verbs or verbsets. It contents @. SET SVF-BOUNDARY = S-BOUNDARY OR VFIN ; # This set is ment to use in rules for disambiguating due to verbs or verbsets. # Here we search for either an S-BOUNDARY or a finite verb, either aux or main. SET CCCOMMA = CC OR COMMA ; # remember that those are potential sentence boundaries, too #!! !Multilingual sets #!! Conjunction sets SET AHTE = ("ahte" CC ) OR ("ahte" CS ) OR ("et" CC ) OR ("et" CS ) ; #!! !Syntactic sets # -------------- LIST ALLSYNTAG = (@+FAUXV) (@+FMAINV) (@-FAUXV) (@-FMAINV) (@-FSUBJ>)(@-FOBJ)(@-F)(@>A) (@>ADVL) (@ADVL<) (@) (@ADVL) (@HAB>) (@N) (@APP) (@APP-N<) (@APP-Pron<) (@APP>Pron) (@APP-Num<) (@APP-ADVL<) (@VOC) (@CNP) (@CVP) (@P<) (@>P) (@HNOUN) (@INTERJ) (@Pron<) (@OBJ) (@OBJ>) (@) (@SPRED) (@PPRED) (@Num<) (@SUBJ) (@) (@X); #!! ALLSYNTAG SET NON-APP = ALLSYNTAG - (@APP); #!! NON-APP #!! ''These were the set types.''