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

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

1 Aug 2021ACL 2021 5archive 2025-07-28

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

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.

PaperPDFCode

Syntology This paper has no arXiv id in the archive, and this site joins papers to Syntology's graph by arXiv id, so this page does not say whether the graph holds it.

Code

microsoft/KC officialpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Multi-Level Knowledge Distillation for Out-of-Distribution Detection in Text (arXiv:2211.11300; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Knowledge Base Question AnsweringQuestion AnsweringSemantic Parsing

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Knowledge Base Question Answering GrailQA ReTraCk Compositional EM 61.5 #1 of 2 Archive leaderboard report
Knowledge Base Question Answering GrailQA ReTraCk Compositional F1 70.9 #1 of 2 Archive leaderboard report
Knowledge Base Question Answering GrailQA ReTraCk I.I.D. EM 84.4 #1 of 2 Archive leaderboard report
Knowledge Base Question Answering GrailQA ReTraCk I.I.D. F1 87.5 #1 of 2 Archive leaderboard report
Knowledge Base Question Answering GrailQA ReTraCk Overall EM 58.1 #1 of 2 Archive leaderboard report
Knowledge Base Question Answering GrailQA ReTraCk Overall F1 65.3 #1 of 2 Archive leaderboard report
Knowledge Base Question Answering GrailQA ReTraCk Zero-shot EM 44.6 #1 of 2 Archive leaderboard report
Knowledge Base Question Answering GrailQA ReTraCk Zero-shot F1 52.5 #1 of 2 Archive leaderboard report
Knowledge Base Question Answering WebQuestionsSP ReTraCk Oracle EL F1 74.7 #6 of 8 Archive leaderboard report
Knowledge Base Question Answering WebQuestionsSP ReTraCk Oracle EL Hits@1 74.6 #6 of 8 Archive leaderboard report
Knowledge Base Question Answering WebQuestionsSP ReTraCk F1 71 #7 of 8 Archive leaderboard report
Knowledge Base Question Answering WebQuestionsSP ReTraCk Hits@1 71.6 #7 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections