Web-scale Surface and Syntactic n-gram Features for Dependency Parsing
Computation and Language
2015-02-26 v1
Abstract
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 -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 -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% absolute UAS improvements on newswire and 1.4% on web text.
Cite
@article{arxiv.1502.07038,
title = {Web-scale Surface and Syntactic n-gram Features for Dependency Parsing},
author = {Dominick Ng and Mohit Bansal and James R. Curran},
journal= {arXiv preprint arXiv:1502.07038},
year = {2015}
}