AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Graph-Based Transformer with Cross-Candidate Verification for Semantic Parsing

Bo Shao, Yeyun Gong, Weizhen Qi, Guihong Cao, Jianshu Ji, Xiaola Lin

AAAI 2020 · Graph learning › Knowledge and temporal graphs · approach: Graph-based dialog systems · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add cross-candidate verification (ablation)GTCV · TOP testexact match accuracy: 81.16 -> 82.51Improved
add graph-based matching (ablation)GTCV · TOP testexact match accuracy: 81.26 -> 82.51Improved
add graph matching and verification on top of BERT rerankerBERT reranker · TOP testexact match accuracy: 80.15 -> 82.51Improved
add GTCV reranking to seq2seq generationseq2seq generation · TOP testexact match accuracy: 77.40 -> 82.51Improved
add GTCV rerankingseq2seq generation · ATISaccuracy: 82.4 -> 87.3Improved
add GTCV rerankingseq2seq generation · JOBSaccuracy: 89.3 -> 92.9Improved
add GTCV rerankingseq2seq generation · TOP in-domain subsetexact match accuracy: 79.82 -> 85.84Improved
replace BERT reranker with GTCVreranker · JOBSaccuracy: 90.1 -> 92.9Improved
increase candidate number from 3 to 10 for cross-candidate verification (ablation)GTCV · TOP testexact match accuracy: 80.01 -> 82.51Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy