Paper: LIMSI’s participation to the 2013 shared task on Native Language Identification

ACL ID W13-1733
Title LIMSI’s participation to the 2013 shared task on Native Language Identification
Venue Innovative Use of NLP for Building Educational Applications
Session
Year 2013
Authors

This paper describes LIMSI?s participation to the first shared task on Native Language Iden- tification. Our submission uses a Maximum Entropy classifier, using as features character and chunk n-grams, spelling and grammati- cal mistakes, and lexical preferences. Perfor- mance was slightly improved by using a two- step classifier to better distinguish otherwise easily confused native languages.