TY - GEN
T1 - Neural Adversarial Training for Semi-supervised Japanese Predicate-argument Structure Analysis
AU - Kurita, Shuhei
AU - Kawahara, Daisuke
AU - Kurohashi, Sadao
N1 - Funding Information:
This work was supported by JST CREST Grant Number JPMJCR1301, Japan and JST ACT-I Grant Number JPMJPR17U8, Japan.
Publisher Copyright:
© 2018 Association for Computational Linguistics
PY - 2018
Y1 - 2018
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85063108156&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85063108156&partnerID=8YFLogxK
U2 - 10.18653/v1/p18-1044
DO - 10.18653/v1/p18-1044
M3 - Conference contribution
AN - SCOPUS:85063108156
T3 - ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
SP - 474
EP - 484
BT - ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
PB - Association for Computational Linguistics (ACL)
T2 - 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
Y2 - 15 July 2018 through 20 July 2018
ER -