ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering
By Shuang Chen, Qian Liu, Zhiwei Yu, Chin-Yew Lin, Jian-Guang Lou, Feng Jiang. 2021
83 citations recorded by the source corpus.
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.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Caiming Xiong
- Kazuma Hashimoto
- Xi Ye
- Semih Yavuz
- Yingbo Zhou
- Richard Socher
- Bryan McCann
- Mohit Bansal
Citations in the corpus
- RNG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering (2021, methodology): “However, ReTrack fails in generalizing to unseen KB Schema items and only achieves poor performance in zero-shot setting, whereas our approach is generalizable and beats ReTrack with a margin of 16.1 F1.”
- Retrieval-Augmented Generation for AI-Generated Content: A Survey (2024, unknown): “ReTraCk [305] links entities using mention detection, and retrieves schema items using dense retriever Bert.”
- Graph Retrieval-Augmented Generation: A Survey (2024, unknown): “While, GraphRAG methods leverage explicit entity and relationship representations in graph data, enabling precise answers by retrieving relevant structured information.”