UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering
Barlas Oguz, Xilun Chen, Vladimir Karpukhin, Stan Peshterliev, Dmytro Okhonko, Michael Schlichtkrull, Sonal Gupta, Yashar Mehdad, Scott Yih
Abstract
We study open-domain question answering with structured, unstructured and semi-structured knowledge sources, including text, tables, lists and knowledge bases. Departing from prior work, we propose a unifying approach that homogenizes all sources by reducing them to text and applies the retriever-reader model which has so far been limited to text sources only. Our approach greatly improves the results on knowledge-base QA tasks by 11 points, compared to latest graph-based methods. More importantly, we demonstrate that our unified knowledge (UniK-QA) model is a simple and yet effective way to combine heterogeneous sources of knowledge, advancing the state-of-the-art results on two popular question answering benchmarks, NaturalQuestions and WebQuestions, by 3.5 and 2.6 points, respectively.The code of UniK-QA is available at: https://github.com/facebookresearch/UniK-QA.- Anthology ID:
- 2022.findings-naacl.115
- Volume:
- Findings of the Association for Computational Linguistics: NAACL 2022
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1535–1546
- Language:
- URL:
- https://aclanthology.org/2022.findings-naacl.115
- DOI:
- 10.18653/v1/2022.findings-naacl.115
- Cite (ACL):
- Barlas Oguz, Xilun Chen, Vladimir Karpukhin, Stan Peshterliev, Dmytro Okhonko, Michael Schlichtkrull, Sonal Gupta, Yashar Mehdad, and Scott Yih. 2022. UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 1535–1546, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering (Oguz et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.findings-naacl.115.pdf
- Code
- facebookresearch/UniK-QA
- Data
- Natural Questions, TQA, TriviaQA, WebQuestions, WebQuestionsSP