RNG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering

Xi Ye, Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou, Caiming Xiong


Abstract
Existing KBQA approaches, despite achieving strong performance on i.i.d. test data, often struggle in generalizing to questions involving unseen KB schema items. Prior ranking-based approaches have shown some success in generalization, but suffer from the coverage issue. We present RnG-KBQA, a Rank-and-Generate approach for KBQA, which remedies the coverage issue with a generation model while preserving a strong generalization capability. Our approach first uses a contrastive ranker to rank a set of candidate logical forms obtained by searching over the knowledge graph. It then introduces a tailored generation model conditioned on the question and the top-ranked candidates to compose the final logical form. We achieve new state-of-the-art results on GrailQA and WebQSP datasets. In particular, our method surpasses the prior state-of-the-art by a large margin on the GrailQA leaderboard. In addition, RnG-KBQA outperforms all prior approaches on the popular WebQSP benchmark, even including the ones that use the oracle entity linking. The experimental results demonstrate the effectiveness of the interplay between ranking and generation, which leads to the superior performance of our proposed approach across all settings with especially strong improvements in zero-shot generalization.
Anthology ID:
2022.acl-long.417
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:
6032–6043
Language:
URL:
https://aclanthology.org/2022.acl-long.417
DOI:
10.18653/v1/2022.acl-long.417
Bibkey:
Cite (ACL):
Xi Ye, Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou, and Caiming Xiong. 2022. RNG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6032–6043, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
RNG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering (Ye et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.417.pdf
Software:
 2022.acl-long.417.software.zip
Video:
 https://aclanthology.org/2022.acl-long.417.mp4
Code
 salesforce/rng-kbqa