Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering

Mingxuan Ju, Wenhao Yu, Tong Zhao, Chuxu Zhang, Yanfang Ye


Abstract
A common thread of open-domain question answering (QA) models employs a retriever-reader pipeline that first retrieves a handful of relevant passages from Wikipedia and then peruses the passages to produce an answer. However, even state-of-the-art readers fail to capture the complex relationships between entities appearing in questions and retrieved passages, leading to answers that contradict the facts. In light of this, we propose a novel knowledge graph enhanced passage reader, namely Grape, to improve the reader performance for open-domain QA. Specifically, for each pair of question and retrieved passage, we first construct a localized bipartite graph, attributed to entity embeddings extracted from the intermediate layer of the reader model. Then, a graph neural network learns relational knowledge while fusing graph and contextual representations into the hidden states of the reader model. Experiments on three open-domain QA benchmarks show Grape can improve the state-of-the-art performance by up to 2.2 exact match score with a negligible overhead increase, with the same retriever and retrieved passages. Our code is publicly available at https://github.com/jumxglhf/GRAPE.
Anthology ID:
2022.findings-emnlp.13
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
169–181
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.13
DOI:
Bibkey:
Cite (ACL):
Mingxuan Ju, Wenhao Yu, Tong Zhao, Chuxu Zhang, and Yanfang Ye. 2022. Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 169–181, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering (Ju et al., Findings 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.findings-emnlp.13.pdf