Machine Comprehension Improves Domain-Specific Japanese Predicate-Argument Structure Analysis

Norio Takahashi, Tomohide Shibata, Daisuke Kawahara, Sadao Kurohashi


Abstract
To improve the accuracy of predicate-argument structure (PAS) analysis, large-scale training data and knowledge for PAS analysis are indispensable. We focus on a specific domain, specifically Japanese blogs on driving, and construct two wide-coverage datasets as a form of QA using crowdsourcing: a PAS-QA dataset and a reading comprehension QA (RC-QA) dataset. We train a machine comprehension (MC) model based on these datasets to perform PAS analysis. Our experiments show that a stepwise training method is the most effective, which pre-trains an MC model based on the RC-QA dataset to acquire domain knowledge and then fine-tunes based on the PAS-QA dataset.
Anthology ID:
D19-5814
Volume:
Proceedings of the 2nd Workshop on Machine Reading for Question Answering
Month:
November
Year:
2019
Address:
Hong Kong, China
Venue:
WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
98–104
Language:
URL:
https://aclanthology.org/D19-5814
DOI:
10.18653/v1/D19-5814
Bibkey:
Cite (ACL):
Norio Takahashi, Tomohide Shibata, Daisuke Kawahara, and Sadao Kurohashi. 2019. Machine Comprehension Improves Domain-Specific Japanese Predicate-Argument Structure Analysis. In Proceedings of the 2nd Workshop on Machine Reading for Question Answering, pages 98–104, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Machine Comprehension Improves Domain-Specific Japanese Predicate-Argument Structure Analysis (Takahashi et al., 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/starsem-semeval-split/D19-5814.pdf