Neural Modeling of Multi-Predicate Interactions for Japanese Predicate Argument Structure Analysis

Hiroki Ouchi, Hiroyuki Shindo, Yuji Matsumoto


Abstract
The performance of Japanese predicate argument structure (PAS) analysis has improved in recent years thanks to the joint modeling of interactions between multiple predicates. However, this approach relies heavily on syntactic information predicted by parsers, and suffers from errorpropagation. To remedy this problem, we introduce a model that uses grid-type recurrent neural networks. The proposed model automatically induces features sensitive to multi-predicate interactions from the word sequence information of a sentence. Experiments on the NAIST Text Corpus demonstrate that without syntactic information, our model outperforms previous syntax-dependent models.
Anthology ID:
P17-1146
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Editors:
Regina Barzilay, Min-Yen Kan
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1591–1600
Language:
URL:
https://aclanthology.org/P17-1146
DOI:
10.18653/v1/P17-1146
Bibkey:
Cite (ACL):
Hiroki Ouchi, Hiroyuki Shindo, and Yuji Matsumoto. 2017. Neural Modeling of Multi-Predicate Interactions for Japanese Predicate Argument Structure Analysis. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1591–1600, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Neural Modeling of Multi-Predicate Interactions for Japanese Predicate Argument Structure Analysis (Ouchi et al., ACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/P17-1146.pdf