Adapting a WSJ-Trained Parser to Grammatically Noisy Text

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.

• Type: Conference
• Year: 2008
• Where: ACL
• Authors: Jennifer Foster, Joachim Wagner, Josef van Genabith
• Keywords: ACL 2008, Computational Linguistics, Treebank, Ungrammatical Sentences, Ungrammatical Treebank