Paper: VTEX System Description for the NLI 2013 Shared Task

ACL ID W13-1711
Title VTEX System Description for the NLI 2013 Shared Task
Venue Innovative Use of NLP for Building Educational Applications
Session
Year 2013
Authors

This paper describes the system developed for the NLI 2013 Shared Task, requiring to identify a writer?s native language by some text written in English. I explore the given manually annotated data using word features such as the length, endings and character trigrams. Furthermore, I em- ploy k-NN classification. Modified TFIDF is used to generate a stop-word list auto- matically. The distance between two docu- ments is calculated combining n-grams of word lengths and endings, and character trigrams.