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

Shuhei Kurita, Daisuke Kawahara, Sadao Kurohashi


Abstract
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.
Anthology ID:
P18-1044
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
474–484
Language:
URL:
https://aclanthology.org/P18-1044
DOI:
10.18653/v1/P18-1044
Bibkey:
Cite (ACL):
Shuhei Kurita, Daisuke Kawahara, and Sadao Kurohashi. 2018. Neural Adversarial Training for Semi-supervised Japanese Predicate-argument Structure Analysis. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 474–484, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Neural Adversarial Training for Semi-supervised Japanese Predicate-argument Structure Analysis (Kurita et al., ACL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/remove-xml-comments/P18-1044.pdf
Poster:
 P18-1044.Poster.pdf