Towards End-to-End Open Conversational Machine Reading

Sizhe Zhou, Siru Ouyang, Zhuosheng Zhang, Hai Zhao


Abstract
In open-retrieval conversational machine reading (OR-CMR) task, machines are required to do multi-turn question answering given dialogue history and a textual knowledge base. Existing works generally utilize two independent modules to approach this problem’s two successive sub-tasks: first with a hard-label decision making and second with a question generation aided by various entailment reasoning methods. Such usual cascaded modeling is vulnerable to error propagation and prevents the two sub-tasks from being consistently optimized. In this work, we instead model OR-CMR as a unified text-to-text task in a fully end-to-end style. Experiments on the ShARC and OR-ShARC dataset show the effectiveness of our proposed end-to-end framework on both sub-tasks by a large margin, achieving new state-of-the-art results. Further ablation studies support that our framework can generalize to different backbone models.
Anthology ID:
2023.findings-eacl.154
Volume:
Findings of the Association for Computational Linguistics: EACL 2023
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2064–2076
Language:
URL:
https://aclanthology.org/2023.findings-eacl.154
DOI:
10.18653/v1/2023.findings-eacl.154
Bibkey:
Cite (ACL):
Sizhe Zhou, Siru Ouyang, Zhuosheng Zhang, and Hai Zhao. 2023. Towards End-to-End Open Conversational Machine Reading. In Findings of the Association for Computational Linguistics: EACL 2023, pages 2064–2076, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Towards End-to-End Open Conversational Machine Reading (Zhou et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-eacl.154.pdf
Video:
 https://aclanthology.org/2023.findings-eacl.154.mp4