Contrastive Analysis with Predictive Power: Typology Driven Estimation of Grammatical Error Distributions in ESL

Proceedings of the 19th Conference on Computational Language Learning, pages 94–102, Beijing, China, July 30-31, 2015. c⃝2015 Association for Computational Linguistics Contrastive Analysis with Predictive Power: Typology Driven Estimation of Grammatical Error Distributions in ESL Yevgeni Berzak CSAIL MIT berzak@mit.edu Roi Reichart Technion IIT roiri@ie.technion.ac.il Boris Katz CSAIL MIT boris@mit.edu Abstract This work examines the impact of cross- linguistic transfer on grammatical errors in English as Second Language (ESL) texts. Using a computational framework that for- malizes the theory of Contrastive Analy- sis (CA), we demonstrate that language specific error distributions in ESL writ- ing can be predicted from the typologi- cal properties of the native language and their relation to the typology of English. Our typology driven model enables to ob- tain accurate estimates of such distribu- tions without access to any ESL data for the target languages. Furthermore, we present a strategy for adjusting our method to low-resource languages that lack typo- logical documentation using a bootstrap- ping approach which approximates native language typology from ESL texts. Fi- nally, we show that our framework is in- strumental for linguistic inquiry seeking to identify first language factors that con- tribute to a wide range of difficulties in second language acquisition. 1 Introduction The study of cross-linguistic transfer, whereby properties of a native language influence perfor- mance in a foreign language, has a long tradi- tion in Linguistics and Second Language Acqui- sition (SLA). Much of the linguistic work on this topic was carried out within the framework of Contrastive Analysis (CA), a theoretical approach that aims to explain difficulties in second language learning in terms of the relations between struc- tures in the native and foreign languages. The basic hypothesis of CA was formulated by Lado (1957), who suggested that “we can predict and describe the patterns that will cause difficulty in learning, and those that will not cause difficulty, by comparing systematically the language and cul- ture to be learned with the native language and culture of the student”. In particular, Lado pos- tulated that divergences between the native and foreign languages will negatively affect learning and lead to increased error rates in the foreign lan- guage. This and subsequent hypotheses were soon met with criticism, targeting their lack of ability to provide reliable predictions, leading to an ongoing debate on the extent to which foreign language er- rors can be explained and predicted by examining native language structure. Differently from the SLA tradition, which em- phasizes manual analysis of error case studies (Odlin, 1989), we address the heart of this contro- versy from a computational data-driven perspec- tive, focusing on the issue of predictive power. We provide a formalization of the CA framework, and demonstrate that the relative frequency of gram- matical errors in ESL can be reliably predicted from the typological properties of the native lan- guage and their relation to the typology of English using a regression model. Tested on 14 languages in a leave-one-out fash- ion, our model achieves a Mean Average Error (MAE) …

Content truncated to 500 words