A reranking approach for dependency parsing with variable-sized subtree features

Mo Shen, Daisuke Kawahara, Sadao Kurohashi

研究成果: Conference contribution

5 被引用数 (Scopus)

抄録

Employing higher-order subtree structures in graph-based dependency parsing has shown substantial improvement over the accuracy, however suffers from the inefficiency increasing with the order of subtrees. We present a new reranking approach for dependency parsing that can utilize complex subtree representation by applying efficient subtree selection heuristics. We demonstrate the effectiveness of the approach in experiments conducted on the Penn Treebank and the Chinese Treebank. Our system improves the baseline accuracy from 91.88% to 93.37% for English, and in the case of Chinese from 87.39% to 89.16%.

本文言語English
ホスト出版物のタイトルProceedings of the 26th Pacific Asia Conference on Language, Information and Computation, PACLIC 2012
ページ308-317
ページ数10
出版ステータスPublished - 2012
外部発表はい
イベント26th Pacific Asia Conference on Language, Information and Computation, PACLIC 2012 - Bali, Indonesia
継続期間: 2012 11 72012 11 7

出版物シリーズ

名前Proceedings of the 26th Pacific Asia Conference on Language, Information and Computation, PACLIC 2012

Conference

Conference26th Pacific Asia Conference on Language, Information and Computation, PACLIC 2012
国/地域Indonesia
CityBali
Period12/11/712/11/7

ASJC Scopus subject areas

  • 情報システム
  • ソフトウェア

フィンガープリント

「A reranking approach for dependency parsing with variable-sized subtree features」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル