ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering

Shuang Chen, Qian Liu, Zhiwei Yu, Chin-Yew Lin, Jian-Guang Lou, Feng Jiang

Abstract
We present Retriever-Transducer-Checker (ReTraCk), a neural semantic parsing framework for large scale knowledge base question answering (KBQA). ReTraCk is designed as a modular framework to maintain high flexibility. It includes a retriever to retrieve relevant KB items efficiently, a transducer to generate logical form with syntax correctness guarantees and a checker to improve transduction procedure. ReTraCk is ranked at top1 overall performance on the GrailQA leaderboard and obtains highly competitive performance on the typical WebQuestionsSP benchmark. Our system can interact with users timely, demonstrating the efficiency of the proposed framework.
Anthology ID:
2021.acl-demo.39
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations
Month:
August
Year:
2021
Address:
Online
Editors:
Heng Ji, Jong C. Park, Rui Xia
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
325–336
Language:
URL:
https://aclanthology.org/2021.acl-demo.39
DOI:
10.18653/v1/2021.acl-demo.39
Bibkey:
Cite (ACL):
Shuang Chen, Qian Liu, Zhiwei Yu, Chin-Yew Lin, Jian-Guang Lou, and Feng Jiang. 2021. ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations, pages 325–336, Online. Association for Computational Linguistics.
Cite (Informal):
ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering (Chen et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-bitext-workshop/2021.acl-demo.39.pdf
Video:
 https://preview.aclanthology.org/ingest-bitext-workshop/2021.acl-demo.39.mp4
Code
 microsoft/KC
Data
GrailQA, WebQuestionsSP
PDF Search Code Video