Using N-gram and Word Network Features for Native Language Identification
Shibamouli Lahiri, Rada F. Mihalcea · 2013
We report on the performance of two different feature sets in the Native Language Identification Shared Task (Tetreault et al., 2013). Our feature sets were inspired by existing literature on native language identification and word networks. Exper-iments show that word networks have competitive performance against the baseline feature set, which is a promising result. We also present a discussion of feature analysis based on information gain, and an overview on the performance of different word net-work features in the Native Language Identification task.