A Three-step Method for Multi-Hop Inference Explanation Regeneration

Yuejia Xiang, Yunyan Zhang, Xiaoming Shi, Bo Liu, Wandi Xu, Xi Chen

Abstract
Multi-hop inference for explanation generation is to combine two or more facts to make an inference. The task focuses on generating explanations for elementary science questions. In the task, the relevance between the explanations and the QA pairs is of vital importance. To address the task, a three-step framework is proposed. Firstly, vector distance between two texts is utilized to recall the top-K relevant explanations for each question, reducing the calculation consumption. Then, a selection module is employed to choose those most relative facts in an autoregressive manner, giving a preliminary order for the retrieved facts. Thirdly, we adopt a re-ranking module to re-rank the retrieved candidate explanations with relevance between each fact and the QA pairs. Experimental results illustrate the effectiveness of the proposed framework with an improvement of 39.78% in NDCG over the official baseline.
Anthology ID:
2021.textgraphs-1.19
Volume:
Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)
Month:
June
Year:
2021
Address:
Mexico City, Mexico
Venue:
TextGraphs
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
171–175
Language:
URL:
https://aclanthology.org/2021.textgraphs-1.19
DOI:
10.18653/v1/2021.textgraphs-1.19
Bibkey:
Cite (ACL):
Yuejia Xiang, Yunyan Zhang, Xiaoming Shi, Bo Liu, Wandi Xu, and Xi Chen. 2021. A Three-step Method for Multi-Hop Inference Explanation Regeneration. In Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15), pages 171–175, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
A Three-step Method for Multi-Hop Inference Explanation Regeneration (Xiang et al., TextGraphs 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nodalida-main-page/2021.textgraphs-1.19.pdf
PDF Search