Paper: Punctuation: Making a Point in Unsupervised Dependency Parsing

ACL ID W11-0303
Title Punctuation: Making a Point in Unsupervised Dependency Parsing
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2011
Authors

We show how punctuation can be used to im- prove unsupervised dependency parsing. Our linguistic analysis confirms the strong connec- tion between English punctuation and phrase boundaries in the Penn Treebank. However, approaches that naively include punctuation marks in the grammar (as if they were words) do not perform well with Klein and Manning’s Dependency Model with Valence (DMV). In- stead, we split a sentence at punctuation and impose parsing restrictions over its fragments. Our grammar inducer is trained on the Wall Street Journal (WSJ) and achieves 59.5% ac- curacy out-of-domain (Brown sentences with 100 or fewer words), more than 6% higher than the previous best results. Further evalu- ation, using the 2006/7 CoNLL sets, reveals that punctuation aids grammar induction in 17 o...