Paper: Web-Scale Features for Full-Scale Parsing

ACL ID P11-1070
Title Web-Scale Features for Full-Scale Parsing
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2011

Counts from large corpora (like the web) can be powerful syntactic cues. Past work has used web counts to help resolve isolated am- biguities, such as binary noun-verb PP attach- ments and noun compound bracketings. In this work, we first present a method for gener- ating web count features that address the full range of syntactic attachments. These fea- tures encode both surface evidence of lexi- cal affinities as well as paraphrase-based cues to syntactic structure. We then integrate our features into full-scale dependency and con- stituent parsers. We show relative error re- ductions of 7.0% over the second-order depen- dency parser of McDonald and Pereira (2006), 9.2% over the constituent parser of Petrov et al. (2006), and 3.4% over a non-local con- stituent reranker.