Web-scale Surface and Syntactic n-gram Features for Dependency Parsing

02/25/2015

∙

by   Dominick Ng, et al.

∙

0

∙

share

We develop novel first- and second-order features for dependency parsing based on the Google Syntactic Ngrams corpus, a collection of subtree counts of parsed sentences from scanned books. We also extend previous work on surface n-gram features from Web1T to the Google Books corpus and from first-order to second-order, comparing and analysing performance over newswire and web treebanks. Surface and syntactic n-grams both produce substantial and complementary gains in parsing accuracy across domains. Our best system combines the two feature sets, achieving up to 0.8 1.4