Learning reliability of parses for domain adaptation of dependency parsing

Daisuke Kawahara, Kiyotaka Uchimoto

研究成果: Conference contribution

22 被引用数 (Scopus)

抄録

The accuracy of parsing has exceeded 90% recently, but this is not high enough to use parsing results practically in natural language processing (NLP) applications such as paraphrase acquisition and relation extraction. We present a method for detecting reliable parses out of the outputs of a single dependency parser. This technique is also applied to domain adaptation of dependency parsing. Our goal was to improve the performance of a state-of-the-art dependency parser on the data set of the domain adaptation track of the CoNLL 2007 shared task, a formidable challenge.

本文言語English
ホスト出版物のタイトルIJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference
出版社Association for Computational Linguistics (ACL)
ページ709-714
ページ数6
ISBN(電子版)9780000000002
出版ステータスPublished - 2008
外部発表はい
イベント3rd International Joint Conference on Natural Language Processing, IJCNLP 2008 - Hyderabad, India
継続期間: 2008 1月 72008 1月 12

出版物シリーズ

名前IJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference
2

Conference

Conference3rd International Joint Conference on Natural Language Processing, IJCNLP 2008
国/地域India
CityHyderabad
Period08/1/708/1/12

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

「Learning reliability of parses for domain adaptation of dependency parsing」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