PGL at TextGraphs 2020 Shared Task: Explanation Regeneration using Language and Graph Learning Methods

Weibin Li, Yuxiang Lu, Zhengjie Huang, Weiyue Su, Jiaxiang Liu, Shikun Feng, Yu Sun


Abstract
This paper describes the system designed by the Baidu PGL Team which achieved the first place in the TextGraphs 2020 Shared Task. The task focuses on generating explanations for elementary science questions. Given a question and its corresponding correct answer, we are asked to select the facts that can explain why the answer is correct for the question and answering (QA) from a large knowledge base. To address this problem, we use a pre-trained language model to recall the top-K relevant explanations for each question. Then, we adopt a re-ranking approach based on a pre-trained language model to rank the candidate explanations. To further improve the rankings, we also develop an architecture consisting both powerful pre-trained transformers and GNNs to tackle the multi-hop inference problem. The official evaluation shows that, our system can outperform the second best system by 1.91 points.
Anthology ID:
2020.textgraphs-1.11
Volume:
Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs)
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Venue:
TextGraphs
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
98–102
Language:
URL:
https://aclanthology.org/2020.textgraphs-1.11
DOI:
10.18653/v1/2020.textgraphs-1.11
Bibkey:
Cite (ACL):
Weibin Li, Yuxiang Lu, Zhengjie Huang, Weiyue Su, Jiaxiang Liu, Shikun Feng, and Yu Sun. 2020. PGL at TextGraphs 2020 Shared Task: Explanation Regeneration using Language and Graph Learning Methods. In Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs), pages 98–102, Barcelona, Spain (Online). Association for Computational Linguistics.
Cite (Informal):
PGL at TextGraphs 2020 Shared Task: Explanation Regeneration using Language and Graph Learning Methods (Li et al., TextGraphs 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.textgraphs-1.11.pdf
Code
 PaddlePaddle/PGL +  additional community code