Explicit Alignment and Many-to-many Entailment Based Reasoning for Conversational Machine Reading

Yangyang Luo, Shiyu Tian, Caixia Yuan, Xiaojie Wang


Abstract
Conversational Machine Reading (CMR) requires answering a user’s initial question through multi-turn dialogue interactions based on a given document. Although there exist many effective methods, they largely neglected the alignment between the document and the user-provided information, which significantly affects the intermediate decision-making and subsequent follow-up question generation. To address this issue, we propose a pipeline framework that (1) aligns the aforementioned two sides in an explicit way, (2) makes decisions using a lightweight many-to-many entailment reasoning module, and (3) directly generates follow-up questions based on the document and previously asked questions. Our proposed method achieves state-of-the-art in micro-accuracy and ranks the first place on the public leaderboard of the CMR benchmark dataset ShARC.
Anthology ID:
2023.findings-emnlp.866
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13009–13022
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.866
DOI:
10.18653/v1/2023.findings-emnlp.866
Bibkey:
Cite (ACL):
Yangyang Luo, Shiyu Tian, Caixia Yuan, and Xiaojie Wang. 2023. Explicit Alignment and Many-to-many Entailment Based Reasoning for Conversational Machine Reading. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 13009–13022, Singapore. Association for Computational Linguistics.
Cite (Informal):
Explicit Alignment and Many-to-many Entailment Based Reasoning for Conversational Machine Reading (Luo et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2023.findings-emnlp.866.pdf