FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answering
Lingxi Zhang, Jing Zhang, Yanling Wang, Shulin Cao, Xinmei Huang, Cuiping Li, Hong Chen, Juanzi Li
Abstract
The generalization problem on KBQA has drawn considerable attention. Existing research suffers from the generalization issue brought by the entanglement in the coarse-grained modeling of the logical expression, or inexecutability issues due to the fine-grained modeling of disconnected classes and relations in real KBs. We propose a Fine-to-Coarse Composition framework for KBQA (FC-KBQA) to both ensure the generalization ability and executability of the logical expression. The main idea of FC-KBQA is to extract relevant fine-grained knowledge components from KB and reformulate them into middle-grained knowledge pairs for generating the final logical expressions. FC-KBQA derives new state-of-the-art performance on GrailQA and WebQSP, and runs 4 times faster than the baseline. Our code is now available at GitHub https://github.com/RUCKBReasoning/FC-KBQA.
BibTeX
@inproceedings{zhang-etal-2023-fc,
title = "{FC}-{KBQA}: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answering",
author = "Zhang, Lingxi and
Zhang, Jing and
Wang, Yanling and
Cao, Shulin and
Huang, Xinmei and
Li, Cuiping and
Chen, Hong and
Li, Juanzi",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.57/",
doi = "10.18653/v1/2023.acl-long.57",
pages = "1002--1017"
}