Word Alignment-Based Evaluation of Uniform Meaning Representations
This work addresses a domain-specific problem for researchers in computational linguistics and natural language processing, focusing on improving evaluation methods for semantic representations, and is incremental as it builds on prior approaches like smatch.
The paper tackles the challenge of evaluating graph-based meaning representations by proposing a node-matching algorithm that uses word alignments inherent in Uniform Meaning Representations (UMR), making comparisons more intuitive and interpretable while avoiding the NP-hard search problem of existing methods like smatch.
Comparison and evaluation of graph-based representations of sentence meaning is a challenge because competing representations of the same sentence may have different number of nodes, and it is not obvious which nodes should be compared to each other. Existing approaches favor node mapping that maximizes $F_1$ score over node relations and attributes, regardless whether the similarity is intentional or accidental; consequently, the identified mismatches in values of node attributes are not useful for any detailed error analysis. We propose a node-matching algorithm that allows comparison of multiple Uniform Meaning Representations (UMR) of one sentence and that takes advantage of node-word alignments, inherently available in UMR. We compare it with previously used approaches, in particular smatch (the de-facto standard in AMR evaluation), and argue that sensitivity to word alignment makes the comparison of meaning representations more intuitive and interpretable, while avoiding the NP-hard search problem inherent in smatch. A script implementing the method is freely available.