Adapting Grammatical Error Correction Based on the Native Language of Writers with Neural Network Joint Models

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1901–1911, Austin, Texas, November 1-5, 2016. c⃝2016 Association for Computational Linguistics Adapting Grammatical Error Correction Based on the Native Language of Writers with Neural Network Joint Models Shamil Chollampatt1 and Duc Tam Hoang2 and Hwee Tou Ng1,2 1NUS Graduate School for Integrative Sciences and Engineering 2Department of Computer Science National University of Singapore shamil@u.nus.edu, {hoangdt,nght}@comp.nus.edu.sg Abstract An important aspect for the task of grammat- ical error correction (GEC) that has not yet been adequately explored is adaptation based on the native language (L1) of writers, despite the marked influences of L1 on second lan- guage (L2) writing. In this paper, we adapt a neural network joint model (NNJM) using L1-specific learner text and integrate it into a statistical machine translation (SMT) based GEC system. Specifically, we train an NNJM on general learner text (not L1-specific) and subsequently train on L1-specific data using a Kullback-Leibler divergence regularized ob- jective function in order to preserve gener- alization of the model. We incorporate this adapted NNJM as a feature in an SMT-based English GEC system and show that adapta- tion achieves significant F0.5 score gains on English texts written by L1 Chinese, Russian, and Spanish writers. 1 Introduction Grammatical error correction (GEC) deals with the automatic correction of errors (spelling, grammar, and collocation errors), particularly in non-native written text. The native language (L1) background of the writer has a noticeable influence on the er- rors made in second language (L2) writing, and con- sidering this factor can potentially improve the per- formance of GEC systems. For example, consider the following sentence written by a Finnish writer (Jarvis and Odlin, 2000): “When they had escaped in the police car they sat under the tree.” The prepo- sition in appears to be grammatically correct. How- ever, in the given context, the preposition ‘from’ is the correct choice in place of the preposition ‘in’. Finnish learners of English tend to overgeneralize the use of the preposition ‘in’. Knowledge of L1 makes the correction more probable whenever the preposition in appears in texts written by Finnish writers. Similarly, Chinese learners of English tend to make frequent verb tense and verb form errors, since Chinese lacks verb inflection (Shaughnessy, 1977). The cross-linguistic influence of L1 on L2 writing is a highly complex phenomenon, and the er- rors made by learners cannot be directly attributed to the similarities or differences between the two lan- guages. As Ortega (2009) points out, learners seem to operate on two complementary principles: “what works in L1 may work in L2 because human lan- guages are fundamentally alike; but if it sounds too L1-like, it will probably not work in L2”. In this paper, we follow a data-driven approach to model these influences and adapt GEC systems using L2 texts written by writers of the same L1 background. The two most popular approaches for grammat- ical error correction are the classification approach (Dahlmeier et al., 2012; Rozovskaya et al., 2014) and …

Content truncated to 500 words