Exploiting Abstract Meaning Representation for Open-Domain Question Answering

Cunxiang Wang, Zhikun Xu, Qipeng Guo, Xiangkun Hu, Xuefeng Bai, Zheng Zhang, Yue Zhang

Abstract
The Open-Domain Question Answering (ODQA) task involves retrieving and subsequently generating answers from fine-grained relevant passages within a database. Current systems leverage Pretrained Language Models (PLMs) to model the relationship between questions and passages. However, the diversity in surface form expressions can hinder the model’s ability to capture accurate correlations, especially within complex contexts. Therefore, we utilize Abstract Meaning Representation (AMR) graphs to assist the model in understanding complex semantic information. We introduce a method known as Graph-as-Token (GST) to incorporate AMRs into PLMs. Results from Natural Questions (NQ) and TriviaQA (TQ) demonstrate that our GST method can significantly improve performance, resulting in up to 2.44/3.17 Exact Match score improvements on NQ/TQ respectively. Furthermore, our method enhances robustness and outperforms alternative Graph Neural Network (GNN) methods for integrating AMRs. To the best of our knowledge, we are the first to employ semantic graphs in ODQA.
Anthology ID:
2023.findings-acl.131
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:
2083–2096
Language:
URL:
https://aclanthology.org/2023.findings-acl.131
DOI:
10.18653/v1/2023.findings-acl.131
Bibkey:
Cite (ACL):
Cunxiang Wang, Zhikun Xu, Qipeng Guo, Xiangkun Hu, Xuefeng Bai, Zheng Zhang, and Yue Zhang. 2023. Exploiting Abstract Meaning Representation for Open-Domain Question Answering. In Findings of the Association for Computational Linguistics: ACL 2023, pages 2083–2096, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Exploiting Abstract Meaning Representation for Open-Domain Question Answering (Wang et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.findings-acl.131.pdf
PDF Search