CoHS-CQG: Context and History Selection for Conversational Question Generation

Xuan Long Do, Bowei Zou, Liangming Pan, Nancy F. Chen, Shafiq Joty, Ai Ti Aw


Abstract
Conversational question generation (CQG) serves as a vital task for machines to assist humans, such as interactive reading comprehension, through conversations. Compared to traditional single-turn question generation (SQG), CQG is more challenging in the sense that the generated question is required not only to be meaningful, but also to align with the provided conversation. Previous studies mainly focus on how to model the flow and alignment of the conversation, but do not thoroughly study which parts of the context and history are necessary for the model. We believe that shortening the context and history is crucial as it can help the model to optimise more on the conversational alignment property. To this end, we propose CoHS-CQG, a two-stage CQG framework, which adopts a novel CoHS module to shorten the context and history of the input. In particular, it selects the top-p sentences and history turns by calculating the relevance scores of them. Our model achieves state-of-the-art performances on CoQA in both the answer-aware and answer-unaware settings.
Anthology ID:
2022.coling-1.48
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
580–591
Language:
URL:
https://aclanthology.org/2022.coling-1.48
DOI:
Bibkey:
Cite (ACL):
Xuan Long Do, Bowei Zou, Liangming Pan, Nancy F. Chen, Shafiq Joty, and Ai Ti Aw. 2022. CoHS-CQG: Context and History Selection for Conversational Question Generation. In Proceedings of the 29th International Conference on Computational Linguistics, pages 580–591, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
CoHS-CQG: Context and History Selection for Conversational Question Generation (Do et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.48.pdf
Code
 dxlong2000/cohs-cqg
Data
CoQASQuAD