Cross-Lingual Lexico-Semantic Transfer in Language Learning

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 974–983, Berlin, Germany, August 7-12, 2016. c⃝2016 Association for Computational Linguistics Cross-Lingual Lexico-Semantic Transfer in Language Learning Ekaterina Kochmar The ALTA Institute University of Cambridge ek358@cam.ac.uk Ekaterina Shutova Computer Laboratory University of Cambridge es407@cam.ac.uk Abstract Lexico-semantic knowledge of our native language provides an initial foundation for second language learning. In this paper, we investigate whether and to what extent the lexico-semantic models of the native language (L1) are transferred to the sec- ond language (L2). Specifically, we focus on the problem of lexical choice and in- vestigate it in the context of three typolog- ically diverse languages: Russian, Span- ish and English. We show that a statistical semantic model learned from L1 data im- proves automatic error detection in L2 for the speakers of the respective L1. Finally, we investigate whether the semantic model learned from a particular L1 is portable to other, typologically related languages. 1 Introduction Lexico-semantic knowledge of our native lan- guage is one of the factors that underlie our ability to communicate and reason about the world. It is also the knowledge that guides us in the process of second language learning. Lexico-semantic vari- ation across languages (Bach and Chao, 2008) makes lexical choice a challenging task for sec- ond language learners (Odlin, 1989). For instance, the meaning of the English expression pull the trigger is realised as *push the trigger in Russian and Spanish, possibly leading to errors of lexical choice by Russian and Spanish speakers learning English. Our native language (L1) plays an essen- tial role in the process of lexical choice. When choosing between several linguistic realisations in L2, non-native speakers may rely on the lexico- semantic information from L1 and select a trans- lational equivalent that they deem to match their communicative intent best. For example, Russian speakers *do exceptions and offers instead of mak- ing them, and *find decisions instead of finding so- lutions, since in Russian do and make have a sin- gle translational equivalent (delat’), and so do de- cision and solution (resheniye). As a result, non- native speakers who tend to fall back to their L1 translate phrases word-for-word, violating English lexico-semantic conventions. The effect of L1 interference on lexical choice in L2 has been pointed out in a number of stud- ies (Chang et al., 2008; Rozovskaya, 2010; Ro- zovskaya, 2011; Dahlmeier and Ng, 2011). Some of these studies also demonstrated that using L1- specific properties, such as the error patterns of speakers of a given L1 or L1-induced paraphrases, improves the performance of automatic error cor- rection in non-native writing. However, neither of the approaches has constructed a semantic model from L1 data and systematically studied the effects of its transfer onto L2. In addition, most previous work has focused on error correction, bypassing the task of error detection for lexical choice. Lex- ical choice is one of the most challenging tasks for both non-native speakers and automated error detection and correction (EDC) …

Content truncated to 500 words