Learning to Identify Follow-Up Questions in Conversational Question Answering

Souvik Kundu, Qian Lin, Hwee Tou Ng


Abstract
Despite recent progress in conversational question answering, most prior work does not focus on follow-up questions. Practical conversational question answering systems often receive follow-up questions in an ongoing conversation, and it is crucial for a system to be able to determine whether a question is a follow-up question of the current conversation, for more effective answer finding subsequently. In this paper, we introduce a new follow-up question identification task. We propose a three-way attentive pooling network that determines the suitability of a follow-up question by capturing pair-wise interactions between the associated passage, the conversation history, and a candidate follow-up question. It enables the model to capture topic continuity and topic shift while scoring a particular candidate follow-up question. Experiments show that our proposed three-way attentive pooling network outperforms all baseline systems by significant margins.
Anthology ID:
2020.acl-main.90
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:
959–968
Language:
URL:
https://aclanthology.org/2020.acl-main.90
DOI:
10.18653/v1/2020.acl-main.90
Bibkey:
Cite (ACL):
Souvik Kundu, Qian Lin, and Hwee Tou Ng. 2020. Learning to Identify Follow-Up Questions in Conversational Question Answering. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 959–968, Online. Association for Computational Linguistics.
Cite (Informal):
Learning to Identify Follow-Up Questions in Conversational Question Answering (Kundu et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.90.pdf
Video:
 http://slideslive.com/38929302