METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation

Ruixin Hong, Hongming Zhang, Xintong Yu, Changshui Zhang


Abstract
Knowing the reasoning chains from knowledge to the predicted answers can help construct an explainable question answering (QA) system. Advances on QA explanation propose to explain the answers with entailment trees composed of multiple entailment steps. While current work proposes to generate entailment trees with end-to-end generative models, the steps in the generated trees are not constrained and could be unreliable. In this paper, we propose METGEN, a Module-based Entailment Tree GENeration framework that has multiple modules and a reasoning controller. Given a question and several supporting knowledge, METGEN can iteratively generate the entailment tree by conducting single-step entailment with separate modules and selecting the reasoning flow with the controller. As each module is guided to perform a specific type of entailment reasoning, the steps generated by METGEN are more reliable and valid. Experiment results on the standard benchmark show that METGEN can outperform previous state-of-the-art models with only 9% of the parameters.
Anthology ID:
2022.findings-naacl.145
Volume:
Findings of the Association for Computational Linguistics: NAACL 2022
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1887–1905
Language:
URL:
https://aclanthology.org/2022.findings-naacl.145
DOI:
10.18653/v1/2022.findings-naacl.145
Bibkey:
Cite (ACL):
Ruixin Hong, Hongming Zhang, Xintong Yu, and Changshui Zhang. 2022. METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 1887–1905, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation (Hong et al., Findings 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2022.findings-naacl.145.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-4/2022.findings-naacl.145.mp4
Code
 Raising-hrx/MetGen +  additional community code
Data
EntailmentBankOpenBookQAQASCeQASC