Graph Reasoning for Question Answering with Triplet Retrieval

Shiyang Li, Yifan Gao, Haoming Jiang, Qingyu Yin, Zheng Li, Xifeng Yan, Chao Zhang, Bing Yin


Abstract
Answering complex questions often requires reasoning over knowledge graphs (KGs). State-of-the-art methods often utilize entities in questions to retrieve local subgraphs, which are then fed into KG encoder, e.g. graph neural networks (GNNs), to model their local structures and integrated into language models for question answering. However, this paradigm constrains retrieved knowledge in local subgraphs and discards more diverse triplets buried in KGs that are disconnected but useful for question answering. In this paper, we propose a simple yet effective method to first retrieve the most relevant triplets from KGs and then rerank them, which are then concatenated with questions to be fed into language models. Extensive results on both CommonsenseQA and OpenbookQA datasets show that our method can outperform state-of-the-art up to 4.6% absolute accuracy.
Anthology ID:
2023.findings-acl.208
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3366–3375
Language:
URL:
https://aclanthology.org/2023.findings-acl.208
DOI:
10.18653/v1/2023.findings-acl.208
Bibkey:
Cite (ACL):
Shiyang Li, Yifan Gao, Haoming Jiang, Qingyu Yin, Zheng Li, Xifeng Yan, Chao Zhang, and Bing Yin. 2023. Graph Reasoning for Question Answering with Triplet Retrieval. In Findings of the Association for Computational Linguistics: ACL 2023, pages 3366–3375, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Graph Reasoning for Question Answering with Triplet Retrieval (Li et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2023.findings-acl.208.pdf