Lars Yencken
ABSTRACT
Learning a foreign language is a long, error-prone process, and much of a learner's time is effectively spent studying vocabulary. Many errors occur because words are only partly known, and this makes their mental storage and retrieval problematic. This paper describes how an intelligent interface may take advantage of the access structure of the mental lexicon to help predict the types of mistakes that learners make, and thus compensate for them. We give two examples, firstly a dictionary interface which circumvents the tip-of-the-tongue problem through search-by-similarity, and secondly an adaptive test generator which leverages user errors to generate plausible multiple-choice distractors.
- G. A. Alvarez and P. Cavanagh. The capacity of visual short-term memory is set both by visual information load and by number of objects. Psychological Science: a Journal of the American Psychological Society, 15(2):106--11, Feb. 2004.Google Scholar
- S. Bilac. Intelligent dictionary interface for learners of Japanese. Master's thesis, Tokyo Institute of Technology, Tokyo Institute of Technology, 2002.Google Scholar
- A. Brown and N. Iwashita. Language background and item difficulty: the development of a computer-adaptive test of Japanese. System, 24(2):199--206, 1996.Google ScholarCross Ref
- J. C. Brown, G. A. Frishkoff, and M. Eskenazi. Automatic question generation for vocabulary assessment. In HLT '05: Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, pages 819--826, Vancouver, Canada, 2005. Google ScholarDigital Library
- R. Brown and D. McNeill. The "Tip of the Tongue" Phenomenon. Journal of Verbal Learning and Verbal Behavior, 5:325--337, 1966.Google ScholarCross Ref
- J. Bull and C. McKenna. Blueprint for Computer-Assisted Assessment. Routledge Falmer, London, UK, 2004.Google Scholar
- C. Collins. WordNet Explorer: Applying Visualization Principles to Lexical Semantics. Technical report, 2006.Google Scholar
- J. Halpern, editor. The Kodansha Kanji Learner's Dictionary. Kodansha International, Tokyo, Japan, 1999.Google Scholar
- A. Hoshino, L. Huan, and H. Nakagawa. A Framework for Automatic Generation of Grammar and Vocabulary Questions. In Proceedings of the WorldCALL 2008 Conference, pages 179--182, Fukuoka, Japan, 2008.Google Scholar
- T. Joyce. Lexical access and the mental lexicon for two-kanji compound words: A priming paradigm study. In Proceedings of the 7th International Conference on Conceptual Structures, pages 1--12, Blacksburg, VA, USA, July 1999.Google Scholar
- H. Kunichika, M. Urushima, T. Hirashima, and A. Takeuchi. Realizing Adaptive Questions and Answers for ICALL Systems. In Proceeding of the 2005 Conference on Artificial Intelligence in Education: Supporting Learning through Intelligent and Socially Informed Technology, pages 854--856, Amsterdam, Netherlands, 2005. Google ScholarDigital Library
- B. Laufer. How much lexis is necessary for reading comprehension? In P. Arnaud and H. Bejoint, editors, Vocabulary and Applied Linguistics, pages 126--132. Palgrave Macmillan, London, 1992.Google ScholarCross Ref
- B. Laufer. The lexical plight in second language reading; words you don't know, words you think you know, and words you can't guess. In J. Coady and T. Huckin, editors, Second Language Vocabulary Acquisition, Cambridge Applied Linguistics, pages 20--34. Cambridge University Press, Cambridge, UK, 1997.Google Scholar
- B. Laufer and Z. Goldstein. Testing Vocabulary Knowledge: Size, Strength, and Computer Adaptiveness. Language Learning, 54(3):399--436, Sept. 2004.Google ScholarCross Ref
- S. J. Lupker. Visual word recognition: Theories and findings. In M. J. Snowling and C. Hulme, editors, The Science of Reading: A Handbook, chapter 3. Blackwell Publishing, Carlton, Australia, 2005.Google Scholar
- J. L. McClelland and D. E. Rumelhart. An interactive activation model of context effects in letter perception, Part 1: An account of basic findings. Psychological Review, 88:375--407, 1981.Google ScholarCross Ref
- F. Moerdijk, C. Tiberius, and J. Niestadt. Accessing the ANW dictionary. In Proceedings of the 2008 Workshop on Cognitive Aspects of the Lexicon, pages 18--24, Manchester, UK, 2008. Google ScholarDigital Library
- I. S. P. Nation. Learning Vocabulary in Another Language. Cambridge University Press, Cambridge, UK, 2001.Google ScholarCross Ref
- S. Nikolova, X. Ma, M. Tremaine, and P. Cook. Vocabulary Navigation Made Easier. In Proceedings of the 2010 International Conference on Intelligent User Interfaces, pages 361--364, Hong Kong, China, 2010. Google ScholarDigital Library
- E. Rich. Users are individuals: individualising user models. International Journal of Man-Machine Studies, 18:199--214, 1983.Google ScholarCross Ref
- H. Saito, H. Masuda, and M. Kawakami. Form and sound similarity effects in kanji recognition. Reading and Writing, 10(3 - 5):323--357, Oct. 1998.Google Scholar
- A. L. Strehl, L. Li, E. Wiewiora, J. Langford, and M. L. Littman. PAC model-free reinforcement learning. In Proceedings of the 23rd International Conference on Machine Learning, pages 881--888, Pittsburgh, PA, USA, 2006. Google ScholarDigital Library
- E. Sumita, F. Sugaya, and S. Yamamoto. Measuring non-native speakers' proficiency of English by using a test with automatically-generated fill-in-the-blank questions. In Proceedings of the 2nd Workshop on Building Educational Applications Using NLP, pages 61--68, Ann Arbor, USA, 2005. Google ScholarDigital Library
- K. Tanaka-Ishii and J. Godon. Kansuke: A kanji look-up system based on a few stroke prototype. In Proceedings of 21st International Conference on Computer Processing of Oriental Languages, Sentosa, Singapore, December 2006. Google ScholarDigital Library
- S. Urquhart and C. Weir. Reading in a Second Language: Process, Product and Practice. Longman, New York, USA, 1998.Google Scholar
- C. J. C. H. Watkins and P. Dayan. Techincal Note: Q-Learning. Machine Learning, 8(3-4):279--292, May 1992. Google ScholarDigital Library
- T. N. Wydell, B. Butterworth, and K. Patterson. The inconsistency of consistency effects in reading: The case of Japanese kanji. Journal of Experimental Psychology: Learning, Memory and Cognition, 21(5):1155--1168, 1995.Google ScholarCross Ref
- S.-L. Yeh and J.-L. Li. Role of structure and component in judgments of visual similarity of Chinese characters. Journal of Experimental Psychology: Human Perception and Performance, 28(4):933--947, 2002.Google ScholarCross Ref
- L. Yencken and T. Baldwin. Efficient grapheme-phoneme alignment for Japanese. In Proceedings of the Australasian Language Technology Workshop 2005, pages 143--151, Sydney, Australia, 2005.Google Scholar
- L. Yencken and T. Baldwin. Measuring and predicting orthographic associations: Modelling the similarity of Japanese kanji. In Proceedings of the 22nd International Conference on Computational Linguistics, Manchester, UK, 2008. Google ScholarDigital Library
Index Terms
- Predicting and compensating for lexicon access errors
Recommendations
Lexicon+TX: rapid construction of a multilingual lexicon with under-resourced languages
Most efforts at automatically creating multilingual lexicons require input lexical resources with rich content (e.g. semantic networks, domain codes, semantic categories) or large corpora. Such material is often unavailable and difficult to construct ...
A Statistical View on Bilingual Lexicon Extraction: From Parallel Corpora to Non-parallel Corpora
AMTA '98: Proceedings of the Third Conference of the Association for Machine Translation in the Americas on Machine Translation and the Information SoupWe present two problems for statistically extracting bilingual lexicon: (1) How can noisy parallel corpora be used? (2) How can non-parallel yet comparable corpora be used? We describe our own work and contribution in relaxing the constraint of using ...
Towards a self-extending lexicon
ACL '85: Proceedings of the 23rd annual meeting on Association for Computational LinguisticsThe problem of manually modifying the lexicon appears with any natural language processing program. Ideally, a program should be able to acquire new lexical entries from context, the way people learn. We address the problem of acquiring entire phrases, ...
Comments