Paper: A Learner Corpus-based Approach to Verb Suggestion for ESL

ACL ID P13-2124
Title A Learner Corpus-based Approach to Verb Suggestion for ESL
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013
Authors

We propose a verb suggestion method which uses candidate sets and domain adaptation to incorporate error patterns produced by ESL learners. The candi- date sets are constructed from a large scale learner corpus to cover various error pat- terns made by learners. Furthermore, the model is trained using both a native cor- pus and the learner corpus via a domain adaptation technique. Experiments on two learner corpora show that the candidate sets increase the coverage of error patterns and domain adaptation improves the per- formance for verb suggestion.