Mining Words in the Minds of Second Language Learners: Learner-Specific Word Difficulty

Proceedings of COLING 2012: Technical Papers, pages 799–814, COLING 2012, Mumbai, December 2012. Mining words in the minds of second language learners: learner-specific word difficulty Yo Ehara1,2 Issei Sato3 Hidekazu Oiwa1,2 Hiroshi Nakagawa3 (1) Graduate School of Information Science and Technology, the University of Tokyo, Tokyo, Japan (2) JSPS Research Fellow, Tokyo, Japan (3) Information Technology Center, the University of Tokyo, Tokyo, Japan ④❡❤❛r❛✱s❛t♦✱♦✐✇❛⑥❅r✳❞❧✳✐t❝✳✉✲t♦❦②♦✳❛❝✳❥♣✱ ♥❛❦❛❣❛✇❛❅❞❧✳✐t❝✳✉✲t♦❦②♦✳❛❝✳❥♣ ABSTRACT While there have been many studies on measuring the size of learners’ vocabulary or the vocabulary they should learn, there have been few studies on what kind of words learners actually know. Therefore, we investigated theoretically and practically important models for predicting second language learners’ vocabulary and propose another model for this vocabulary prediction task. With the current models, the same word difficulty measure is shared by all learners. This is unrealistic because some learners have special interests. A learner interested in music may know special music-related terms regardless of their difficulty. To solve this problem, our model can define a learner-specific word difficulty measure. Our model is also an extension of these current models in the sense that these models are special cases of our model. In a qualitative evaluation, we defined a measure for how learner-specific a word is. Interestingly, the word with the highest learner-specificity was “twitter”. Although “twitter” is a difficult English word, some low-ability learners presumably knew this word through the famous micro-blogging service. Our qualitative evaluation successfully extracted such interesting and suggestive examples. Our model achieved an accuracy competitive with the current models. KEYWORDS: Learner-specificity, vocabulary prediction, Rasch model. 799 1 Introduction When learning second languages, vocabulary knowledge is as important as, or sometimes more important, than grammar. The importance of vocabulary knowledge has been a main focus in the last decade in the field of second language acquisition (SLA). Studies regarding vocabulary knowledge of second language learners have been mainly focusing on two major tasks: devising methods for measuring the size of the second language vocabulary of learners for testing purposes (Schmitt et al., 2001; Laufer and Nation, 1999; Nation, 1990) and determining the words that the learners should learn (Nation, 2006). However, there have been few studies on what kind of words learners actually know. This is the basic research question for our research. To study what words second language learners actually know, we focused on the vocabulary prediction task. In this task, we aim to build a model that predicts, given a word and a learner, whether or not the learner knows the word. As far as we know, Ehara et al. (2010) is the only study that dealt directly with the vocabulary prediction task. They applied this task to a reading support user interface for second language learners that automatically identifies the words unfamiliar to the learner on a Web page. The vocabulary prediction task is important for both theory and application. From the theoretical point of view, this task is interesting in that it mines the words second language learners know and creates …

Content truncated to 500 words