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 the 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.
Cite
CITATION STYLE
Chen, S., Liu, Q., Yu, Z., Lin, C. Y., Lou, J. G., & Jiang, F. (2021). ReTraCk: A flexible and efficient framework for knowledge base question answering. In ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the System Demonstrations (pp. 325–336). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2021.acl-demo.39
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
