Incremental prediction of sentence-final verbs: Humans versus machines

Alvin C. Grissom, Naho Orita, Jordan Boyd-Graber

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

Verb prediction is important in human sentence processing and, practically, in simultaneous machine translation. In verb-final languages, speakers select the final verb before it is uttered, and listeners predict it before it is uttered. Simultaneous interpreters must do the same to translate in real-time. Motivated by the problem of SOV-SVO simultaneous machine translation, we provide a study of incremental verb prediction in verb-final languages. As a basis of comparison, we examine incremental verb prediction with human participants in a multiple choice setting using crowdsourcing to gain insight into incremental human performance in a constrained setting. We then examine a computational approach to incremental verb prediction using discriminative classification with shallow features. Both humans and machines predict verbs more accurately as more of a sentence becomes available, and case markers—when available—help humans and sometimes machines predict final verbs.

本文言語English
ホスト出版物のタイトルCoNLL 2016 - 20th SIGNLL Conference on Computational Natural Language Learning, Proceedings
出版社Association for Computational Linguistics (ACL)
ページ95-104
ページ数10
ISBN(電子版)9781945626197
出版ステータスPublished - 2016
外部発表はい
イベント20th SIGNLL Conference on Computational Natural Language Learning, CoNLL 2016 - Berlin, Germany
継続期間: 2016 8 112016 8 12

出版物シリーズ

名前CoNLL 2016 - 20th SIGNLL Conference on Computational Natural Language Learning, Proceedings

Conference

Conference20th SIGNLL Conference on Computational Natural Language Learning, CoNLL 2016
国/地域Germany
CityBerlin
Period16/8/1116/8/12

ASJC Scopus subject areas

  • 人工知能
  • 人間とコンピュータの相互作用
  • 言語学および言語

フィンガープリント

「Incremental prediction of sentence-final verbs: Humans versus machines」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