Teaksta is an intelligent computer-assisted language learning (ICALL) system designed to provide supplementary language learning activity resources to language learners. It can be viewed as an intelligent automatic workbook, providing an unlimited number of activities designed to foster awareness of grammatical forms and functions. Because it is a web-based system, it can be used anywhere there is a computer with internet access.
The Teaksta activities are automatically derived from authentic texts.
Teaksta uses state-of-the-art Natural Language Processing (NLP) technology to generate exercises, identifying targeted lexical and phrasal material through a combination of tokenization, lemmatization, morphological analysis and disambiguation, and shallow syntactic parsing.
The activity types Teaksta provides follow a pedagogically motivated progression from receptive presentation, to productive presentation, to controlled practice. Specifically, activities include the coloring of targeted forms, having the learner find and click on targeted forms, and finally, controlled practice activities such as multiple choice, fill-in-the-blank, or editing tasks. Teaksta provides these activity progressions for a variety of grammar topics.
Teaksta History
Teaksta is an extension of the WERTi system (Working with English Real Texts), which has been under development since 2006.
The original WERTi system was designed by Detmar Meurers, Vanessa Metcalf, Luiz Amaral, Chris Kovach, and Cory Shain at Ohio State University. Work on WERTi continued at the University of Tübingen after Detmar moved there in 2008. The original Python-based code was ported to Java and the UIMA framework by Aleksandar Dimitrov and developed further by Niels Ott and Ramon Ziai. A demo of the first Java version is available for reference. In 2010, Adriane Boyd developed the firefox extension, which improves usability and compatibility, in particular for web pages with dynamically-generated content and special session handling.
We are continually working on new topics and activities and are grateful for ideas and contributions in this area from Magdalena Leshtanska, Emma Li, Iliana Simova, Maria Tchalakova, and Tatiana Vodolazova.
Teaksta - the North Saami version of WERTi has been set up by Heli Uibo. The exercise types (topics) have been worked out by Lene Antonsen.
References
- Detmar Meurers, Ramon Ziai, Luiz Amaral, Adriane Boyd, Aleksandar Dimitrov, Vanessa Metcalf, Niels Ott (2010). Enhancing Authentic Web Pages for Language Learners. Proceedings of the 5th Workshop on Innovative Use of NLP for Building Educational Applications, NAACL-HLT 2010, Los Angeles.
- Aleksandar Dimitrov (2008). Rebuilding WERTi: Providing a Platform for Second Language Acquisition Assistance. Technical report, Seminar für Sprachwissenschaft, Universität Tübingen.
- Niels Ott and Ramon Ziai (2008). ICALL Activities for Gerunds vs. To-infinitives: A Constraint Grammar-based Extension to the New WERTi System. Term paper for the course Using Natural Language Processing to Foster Language Awareness in Second Language Learning, Universität Tübingen, Summer 2008.
- Vanessa Metcalf and Detmar Meurers (2006). Generating Web-based English Preposition Exercises from Real-World Texts. EUROCALL 2006. Granada, Spain. September 4–7, 2006.
- Luiz Amaral, Vanessa Metcalf, Detmar Meurers (2006). Language Awareness through Re-use of NLP Technology. Pre-conference Workshop on NLP in CALL – Computational and Linguistic Challenges. CALICO 2006. University of Hawaii. May 17, 2006.