Open Domain Question Answering with A Unified Knowledge Interface

Kaixin Ma, Hao Cheng, Xiaodong Liu, Eric Nyberg, Jianfeng Gao


Abstract
The retriever-reader framework is popular for open-domain question answering (ODQA) due to its ability to use explicit knowledge. Although prior work has sought to increase the knowledge coverage by incorporating structured knowledge beyond text, accessing heterogeneous knowledge sources through a unified interface remains an open question. While data-to-text generation has the potential to serve as a universal interface for data and text, its feasibility for downstream tasks remains largely unknown. In this work, we bridge this gap and use the data-to-text method as a means for encoding structured knowledge for open-domain question answering. Specifically, we propose a verbalizer-retriever-reader framework for ODQA over data and text where verbalized tables from Wikipedia and graphs from Wikidata are used as augmented knowledge sources. We show that our Unified Data and Text QA, UDT-QA, can effectively benefit from the expanded knowledge index, leading to large gains over text-only baselines. Notably, our approach sets the single-model state-of-the-art on Natural Questions. Furthermore, our analyses indicate that verbalized knowledge is preferred for answer reasoning for both adapted and hot-swap settings.
Anthology ID:
2022.acl-long.113
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1605–1620
Language:
URL:
https://aclanthology.org/2022.acl-long.113
DOI:
10.18653/v1/2022.acl-long.113
Bibkey:
Cite (ACL):
Kaixin Ma, Hao Cheng, Xiaodong Liu, Eric Nyberg, and Jianfeng Gao. 2022. Open Domain Question Answering with A Unified Knowledge Interface. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1605–1620, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Open Domain Question Answering with A Unified Knowledge Interface (Ma et al., ACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2022.acl-long.113.pdf
Video:
 https://preview.aclanthology.org/naacl24-info/2022.acl-long.113.mp4
Code
 mayer123/udt-qa
Data
DARTKELMNatural QuestionsOTT-QAWebQuestions