Boosting-based parse reranking with subtree features

Taku Kudo, Jun Suzuki, Hideki Isozaki

研究成果: Conference contribution

35 被引用数 (Scopus)

抄録

This paper introduces a new application of boosting for parse reranking. Several parsers have been proposed that utilize the all-subtrees representation (e.g., tree kernel and data oriented parsing). This paper argues that such an all-subtrees representation is extremely redundant and a comparable accuracy can be achieved using just a small set of subtrees. We show how the boosting algorithm can be applied to the all-subtrees representation and how it selects a small and relevant feature set efficiently. Two experiments on parse reranking show that our method achieves comparable or even better performance than kernel methods and also improves the testing efficiency.

本文言語English
ホスト出版物のタイトルACL-05 - 43rd Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
出版社Association for Computational Linguistics (ACL)
ページ189-196
ページ数8
ISBN(印刷版)1932432515, 9781932432510
DOI
出版ステータスPublished - 2005
外部発表はい
イベント43rd Annual Meeting of the Association for Computational Linguistics, ACL-05 - Ann Arbor, MI, United States
継続期間: 2005 6 252005 6 30

出版物シリーズ

名前ACL-05 - 43rd Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

Other

Other43rd Annual Meeting of the Association for Computational Linguistics, ACL-05
国/地域United States
CityAnn Arbor, MI
Period05/6/2505/6/30

ASJC Scopus subject areas

  • 言語および言語学
  • 言語学および言語

フィンガープリント

「Boosting-based parse reranking with 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