How to Ask Good Questions? Try to Leverage Paraphrases

Xin Jia, Wenjie Zhou, Xu Sun, Yunfang Wu


Abstract
Given a sentence and its relevant answer, how to ask good questions is a challenging task, which has many real applications. Inspired by human’s paraphrasing capability to ask questions of the same meaning but with diverse expressions, we propose to incorporate paraphrase knowledge into question generation(QG) to generate human-like questions. Specifically, we present a two-hand hybrid model leveraging a self-built paraphrase resource, which is automatically conducted by a simple back-translation method. On the one hand, we conduct multi-task learning with sentence-level paraphrase generation (PG) as an auxiliary task to supplement paraphrase knowledge to the task-share encoder. On the other hand, we adopt a new loss function for diversity training to introduce more question patterns to QG. Extensive experimental results show that our proposed model obtains obvious performance gain over several strong baselines, and further human evaluation validates that our model can ask questions of high quality by leveraging paraphrase knowledge.
Anthology ID:
2020.acl-main.545
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6130–6140
Language:
URL:
https://aclanthology.org/2020.acl-main.545
DOI:
10.18653/v1/2020.acl-main.545
Bibkey:
Cite (ACL):
Xin Jia, Wenjie Zhou, Xu Sun, and Yunfang Wu. 2020. How to Ask Good Questions? Try to Leverage Paraphrases. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6130–6140, Online. Association for Computational Linguistics.
Cite (Informal):
How to Ask Good Questions? Try to Leverage Paraphrases (Jia et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2020.acl-main.545.pdf
Dataset:
 2020.acl-main.545.Dataset.zip
Video:
 http://slideslive.com/38928935