AMR Similarity Metrics from Principles
This work addresses the need for reliable evaluation metrics in natural language processing for researchers working with AMR, though it is incremental as it builds on existing metrics.
The paper tackles the problem of evaluating metrics for comparing Abstract Meaning Representation (AMR) graphs by establishing principled criteria, analyzing existing metrics like Smatch and SemBleu to reveal undesirable properties, and proposing a new metric S^2match that better handles slight meaning deviations and meets all criteria, showing advantages over prior methods.
Different metrics have been proposed to compare Abstract Meaning Representation (AMR) graphs. The canonical Smatch metric (Cai and Knight, 2013) aligns the variables of two graphs and assesses triple matches. The recent SemBleu metric (Song and Gildea, 2019) is based on the machine-translation metric Bleu (Papineni et al., 2002) and increases computational efficiency by ablating the variable-alignment. In this paper, i) we establish criteria that enable researchers to perform a principled assessment of metrics comparing meaning representations like AMR; ii) we undertake a thorough analysis of Smatch and SemBleu where we show that the latter exhibits some undesirable properties. For example, it does not conform to the identity of indiscernibles rule and introduces biases that are hard to control; iii) we propose a novel metric S$^2$match that is more benevolent to only very slight meaning deviations and targets the fulfilment of all established criteria. We assess its suitability and show its advantages over Smatch and SemBleu.