Neural Adversarial Training for Semi-supervised Japanese Predicate-argument Structure Analysis

Shuhei Kurita, Daisuke Kawahara, Sadao Kurohashi

研究成果: Conference contribution

1 引用 (Scopus)

抜粋

Japanese predicate-argument structure (PAS) analysis involves zero anaphora resolution, which is notoriously difficult. To improve the performance of Japanese PAS analysis, it is straightforward to increase the size of corpora annotated with PAS. However, since it is prohibitively expensive, it is promising to take advantage of a large amount of raw corpora. In this paper, we propose a novel Japanese PAS analysis model based on semi-supervised adversarial training with a raw corpus. In our experiments, our model outperforms existing state-of-the-art models for Japanese PAS analysis.

元の言語English
ホスト出版物のタイトルACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
出版者Association for Computational Linguistics (ACL)
ページ474-484
ページ数11
ISBN(電子版)9781948087322
DOI
出版物ステータスPublished - 2018
外部発表Yes
イベント56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 - Melbourne, Australia
継続期間: 2018 7 152018 7 20

出版物シリーズ

名前ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
1

Conference

Conference56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
Australia
Melbourne
期間18/7/1518/7/20

ASJC Scopus subject areas

  • Software
  • Computational Theory and Mathematics

フィンガープリント Neural Adversarial Training for Semi-supervised Japanese Predicate-argument Structure Analysis' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

  • これを引用

    Kurita, S., Kawahara, D., & Kurohashi, S. (2018). Neural Adversarial Training for Semi-supervised Japanese Predicate-argument Structure Analysis. : ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) (pp. 474-484). (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); 巻数 1). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/p18-1044