Determining semantic textual similarity using natural deduction proofs

Hitomi Yanaka, Pascual Martínez-Gómez, Koji Mineshima, Daisuke Bekki

研究成果: Conference contribution

6 被引用数 (Scopus)

抄録

Determining semantic textual similarity is a core research subject in natural language processing. Since vector-based models for sentence representation often use shallow information, capturing accurate semantics is difficult. By contrast, logical semantic representations capture deeper levels of sentence semantics, but their symbolic nature does not offer graded notions of textual similarity. We propose a method for determining semantic textual similarity by combining shallow features with features extracted from natural deduction proofs of bidirectional entailment relations between sentence pairs. For the natural deduction proofs, we use ccg2lambda, a higher-order automatic inference system, which converts Combinatory Categorial Grammar (CCG) derivation trees into semantic representations and conducts natural deduction proofs. Experiments show that our system was able to outperform other logic-based systems and that features derived from the proofs are effective for learning textual similarity.

本文言語English
ホスト出版物のタイトルEMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings
出版社Association for Computational Linguistics (ACL)
ページ681-691
ページ数11
ISBN(電子版)9781945626838
DOI
出版ステータスPublished - 2017
外部発表はい
イベント2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017 - Copenhagen, Denmark
継続期間: 2017 9月 92017 9月 11

出版物シリーズ

名前EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings

Conference

Conference2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017
国/地域Denmark
CityCopenhagen
Period17/9/917/9/11

ASJC Scopus subject areas

  • コンピュータ サイエンスの応用
  • 情報システム
  • 計算理論と計算数学

フィンガープリント

「Determining semantic textual similarity using natural deduction proofs」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