Extracting the Native Language Signal for Second Language Acquisition

Ben Swanson and Eugene Charniak

We develop a method for effective extraction of linguistic patterns that are differentially expressed based on the native language of the author. This method uses multiple corpora to allow for the removal of data set specific patterns, and addresses both feature relevancy and redundancy. We evaluate different relevancy ranking metrics and show that common measures of relevancy can be inappropriate for data with many rare features. Our feature set is a broad class of syntactic patterns, and to better capture the signal we extend the Bayesian Tree Substitution Grammar induction algorithm to a supervised mixture of latent grammars. We show that this extension can be used to extract a larger set of relevant features.