Machine comprehension improves domain-specific japanese predicate-argument structure analysis

Norio Takahashi, Tomohide Shibata, Daisuke Kawahara, Sadao Kurohashi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

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 driv- ing, 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 experi- ments 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.

Original languageEnglish
Title of host publicationMRQA@EMNLP 2019 - Proceedings of the 2nd Workshop on Machine Reading for Question Answering
PublisherAssociation for Computational Linguistics (ACL)
Pages98-104
Number of pages7
ISBN (Electronic)9781950737819
Publication statusPublished - 2019
Externally publishedYes
Event2nd Workshop on Machine Reading for Question Answering, MRQA@EMNLP 2019 - Hong Kong, China
Duration: 2019 Nov 4 → …

Publication series

NameMRQA@EMNLP 2019 - Proceedings of the 2nd Workshop on Machine Reading for Question Answering

Conference

Conference2nd Workshop on Machine Reading for Question Answering, MRQA@EMNLP 2019
Country/TerritoryChina
CityHong Kong
Period19/11/4 → …

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Machine comprehension improves domain-specific japanese predicate-argument structure analysis'. Together they form a unique fingerprint.

Cite this