[go: up one dir, main page]

RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Trees

Tengxiao Liu, Qipeng Guo, Xiangkun Hu, Yue Zhang, Xipeng Qiu, Zheng Zhang


Abstract
Interpreting the reasoning process from questions to answers poses a challenge in approaching explainable QA. A recently proposed structured reasoning format, entailment tree, manages to offer explicit logical deductions with entailment steps in a tree structure. To generate entailment trees, prior single pass sequence-to-sequence models lack visible internal decision probability, while stepwise approaches are supervised with extracted single step data and cannot model the tree as a whole. In this work, we propose RLET, a Reinforcement Learning based Entailment Tree generation framework, which is trained utilising the cumulative signals across the whole tree. RLET iteratively performs single step reasoning with sentence selection and deduction generation modules, from which the training signal is accumulated across the tree with elaborately designed aligned reward function that is consistent with the evaluation. To the best of our knowledge, we are the first to introduce RL into the entailment tree generation task. Experiments on three settings of the EntailmentBank dataset demonstrate the strength of using RL framework.
Anthology ID:
2022.emnlp-main.483
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7177–7189
Language:
URL:
https://aclanthology.org/2022.emnlp-main.483
DOI:
10.18653/v1/2022.emnlp-main.483
Bibkey:
Cite (ACL):
Tengxiao Liu, Qipeng Guo, Xiangkun Hu, Yue Zhang, Xipeng Qiu, and Zheng Zhang. 2022. RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Trees. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 7177–7189, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Trees (Liu et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.483.pdf