Inducing example-based semantic frames from a massive amount of verb uses

Daisuke Kawahara, Daniel W. Peterson, Octavian Popescu, Martha Palmer

研究成果: Conference contribution

17 被引用数 (Scopus)

抄録

We present an unsupervised method for inducing semantic frames from verb uses in giga-word corpora. Our semantic frames are verb-specific example-based frames that are distinguished according to their senses. We use the Chinese Restaurant Process to automatically induce these frames from a massive amount of verb instances. In our experiments, we acquire broad-coverage semantic frames from two giga-word corpora, the larger comprising 20 billion words. Our experimental results indicate the effectiveness of our approach.

本文言語English
ホスト出版物のタイトル14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014
出版社Association for Computational Linguistics (ACL)
ページ58-67
ページ数10
ISBN(印刷版)9781632663962
DOI
出版ステータスPublished - 2014
外部発表はい
イベント14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014 - Gothenburg, Sweden
継続期間: 2014 4月 262014 4月 30

出版物シリーズ

名前14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014

Conference

Conference14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014
国/地域Sweden
CityGothenburg
Period14/4/2614/4/30

ASJC Scopus subject areas

  • ソフトウェア

フィンガープリント

「Inducing example-based semantic frames from a massive amount of verb uses」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