Dependency parse reranking with rich subtree features

Mo Shen, Daisuke Kawahara, Sadao Kurohashi

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

In pursuing machine understanding of human language, highly accurate syntactic analysis is a crucial step. In this work, we focus on dependency grammar, which models syntax by encoding transparent predicate-argument structures. Recent advances in dependency parsing have shown that employing higherorder subtree structures in graph-based parsers can substantially improve the parsing accuracy. However, the inefficiency of this approach increases with the order of the subtrees. This work explores a new reranking approach for dependency parsing that can utilize complex subtree representations by applying efficient subtree selection methods. We demonstrate the effectiveness of the approach in experiments conducted on the Penn Treebank and the Chinese Treebank. Our system achieves the best performance among known supervised systems evaluated on these datasets, improving the baseline accuracy from 91.88% to 93.42% for English, and from 87.39% to 89.25% for Chinese.

Original languageEnglish
Article number2327295
Pages (from-to)1208-1218
Number of pages11
JournalIEEE Transactions on Audio, Speech and Language Processing
Volume22
Issue number7
DOIs
Publication statusPublished - 2014 Jul 1
Externally publishedYes

Keywords

  • Dependency parsing
  • Multilingual parsing
  • Parse reranking

ASJC Scopus subject areas

  • Acoustics and Ultrasonics
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Dependency parse reranking with rich subtree features'. Together they form a unique fingerprint.

  • Cite this