Adapting a WSJ-trained parser to grammatically noisy text

Abstract

We present a robust parser which is trained on a treebank of ungrammatical sentences. The treebank is created automatically by modifying Penn treebank sentences so that they contain one or more syntactic errors. We evaluate an existing Penn-treebank-trained parser on the ungrammatical treebank to see how it reacts to noise in the form of grammatical errors. We re-train this parser on the training section of the ungrammatical treebank, leading to an significantly improved performance on the ungrammatical test sets. We show how a classifier can be used to prevent performance degradation on the original grammatical data.