Papers › Rematch: Robust and Efficient Matching of Local Knowledge Graphs to Improve Structural...

Rematch: Robust and Efficient Matching of Local Knowledge Graphs to Improve Structural and Semantic Similarity

2 Apr 2024Findings of the Association for Computational Linguistics: NAACL 2024 6arXiv:2404.02126archive 2025-07-28

Zoher Kachwala, Jisun An, Haewoon Kwak, Filippo Menczer

Knowledge graphs play a pivotal role in various applications, such as question-answering and fact-checking. Abstract Meaning Representation (AMR) represents text as knowledge graphs. Evaluating the quality of these graphs involves matching them structurally to each other and semantically to the source text. Existing AMR metrics are inefficient and struggle to capture semantic similarity. We also lack a systematic evaluation benchmark for assessing structural similarity between AMR graphs. To overcome these limitations, we introduce a novel AMR similarity metric, rematch, alongside a new evaluation for structural similarity called RARE. Among state-of-the-art metrics, rematch ranks second in structural similarity; and first in semantic similarity by 1--5 percentage points on the STS-B and SICK-R benchmarks. Rematch is also five times faster than the next most efficient metric.

PaperPDFConference PDFCode

Code

osome-iu/Rematch-RARE officialmentioned in papermentioned on GitHub 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.

Code Syntology ran Syntology

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

Tasks

Abstract Meaning RepresentationFact CheckingGraph MatchingKnowledge GraphsQuestion AnsweringSTSSemantic SimilaritySemantic Textual Similarity

1 archive task tag without a task page not shown.

Datasets

Introduced by this paper, per the archive.

RARE

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Matching RARE Rematch Spearman Correlation 95.32 #2 of 5 Archive leaderboard report
Semantic Textual Similarity SICK Rematch Spearman Correlation 0.6772 #20 of 22 Archive leaderboard report
Semantic Textual Similarity STS Benchmark Rematch Spearman Correlation 0.6652 #62 of 66 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