Improving Complex Knowledge Base Question Answering via Question-to-Action and Question-to-Question Alignment

Yechun Tang, Xiaoxia Cheng, Weiming Lu


Abstract
Complex knowledge base question answering can be achieved by converting questions into sequences of predefined actions. However, there is a significant semantic and structural gap between natural language and action sequences, which makes this conversion difficult. In this paper, we introduce an alignment-enhanced complex question answering framework, called ALCQA, which mitigates this gap through question-to-action alignment and question-to-question alignment. We train a question rewriting model to align the question and each action, and utilize a pretrained language model to implicitly align the question and KG artifacts. Moreover, considering that similar questions correspond to similar action sequences, we retrieve top-k similar question-answer pairs at the inference stage through question-to-question alignment and propose a novel reward-guided action sequence selection strategy to select from candidate action sequences. We conduct experiments on CQA and WQSP datasets, and the results show that our approach outperforms state-of-the-art methods and obtains a 9.88% improvements in the F1 metric on CQA dataset. Our source code is available at https://github.com/TTTTTTTTy/ALCQA.
Anthology ID:
2022.emnlp-main.10
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
137–147
Language:
URL:
https://aclanthology.org/2022.emnlp-main.10
DOI:
10.18653/v1/2022.emnlp-main.10
Bibkey:
Cite (ACL):
Yechun Tang, Xiaoxia Cheng, and Weiming Lu. 2022. Improving Complex Knowledge Base Question Answering via Question-to-Action and Question-to-Question Alignment. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 137–147, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Improving Complex Knowledge Base Question Answering via Question-to-Action and Question-to-Question Alignment (Tang et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.10.pdf