Rematch: Robust and Efficient Matching of Local Knowledge Graphs to Improve Structural and Semantic Similarity
This addresses the need for better evaluation tools in natural language processing applications like question-answering and fact-checking, though it is incremental as it builds on existing AMR metrics.
The paper tackled the problem of inefficient and semantically inadequate metrics for evaluating Abstract Meaning Representation (AMR) knowledge graphs by introducing rematch, a new similarity metric, and RARE, a structural similarity evaluation benchmark. The result showed that rematch ranks second in structural similarity and first in semantic similarity by 1-5 percentage points on benchmarks, while being five times faster than the next most efficient metric.
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.