TY - GEN
T1 - Algorithm selection and model adaptation for ESL correction tasks
AU - Rozovskaya, Alla
AU - Roth, Dan
PY - 2011
Y1 - 2011
N2 - We consider the problem of correcting errors made by English as a Second Language (ESL) writers and address two issues that are essential to making progress in ESL error correction - algorithm selection and model adaptation to the first language of the ESL learner. A variety of learning algorithms have been applied to correct ESL mistakes, but often comparisons were made between incomparable data sets. We conduct an extensive, fair comparison of four popular learning methods for the task, reversing conclusions from earlier evaluations. Our results hold for different training sets, genres, and feature sets. A second key issue in ESL error correction is the adaptation of a model to the first language of the writer. Errors made by non-native speakers exhibit certain regularities and, as we show, models perform much better when they use knowledge about error patterns of the nonnative writers. We propose a novel way to adapt a learned algorithm to the first language of the writer that is both cheaper to implement and performs better than other adaptation methods.
AB - We consider the problem of correcting errors made by English as a Second Language (ESL) writers and address two issues that are essential to making progress in ESL error correction - algorithm selection and model adaptation to the first language of the ESL learner. A variety of learning algorithms have been applied to correct ESL mistakes, but often comparisons were made between incomparable data sets. We conduct an extensive, fair comparison of four popular learning methods for the task, reversing conclusions from earlier evaluations. Our results hold for different training sets, genres, and feature sets. A second key issue in ESL error correction is the adaptation of a model to the first language of the writer. Errors made by non-native speakers exhibit certain regularities and, as we show, models perform much better when they use knowledge about error patterns of the nonnative writers. We propose a novel way to adapt a learned algorithm to the first language of the writer that is both cheaper to implement and performs better than other adaptation methods.
UR - http://www.scopus.com/inward/record.url?scp=84859048312&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84859048312&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84859048312
SN - 9781932432879
T3 - ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies
SP - 924
EP - 933
BT - ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics
T2 - 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-HLT 2011
Y2 - 19 June 2011 through 24 June 2011
ER -