Towards a Decomposable Metric for Explainable Evaluation of Text Generation from AMR

TL;DR

This paper introduces a new decomposable metric, $\\mathcal{M}\mathcal{F}_\beta$, for evaluating AMR-to-text generation that emphasizes meaning preservation and linguistic quality, addressing limitations of existing surface matching metrics.

Contribution

It proposes a novel, explainable evaluation metric combining meaning preservation and grammatical form, applicable beyond AMR-to-text tasks.

Findings

The metric improves evaluation reliability for AMR-to-text systems.

It offers explainability by decomposing scores into meaning and form components.

The approach does not depend solely on gold standard references.

Abstract

Systems that generate natural language text from abstract meaning representations such as AMR are typically evaluated using automatic surface matching metrics that compare the generated texts to reference texts from which the input meaning representations were constructed. We show that besides well-known issues from which such metrics suffer, an additional problem arises when applying these metrics for AMR-to-text evaluation, since an abstract meaning representation allows for numerous surface realizations. In this work we aim to alleviate these issues by proposing $\mathcal{M}\mathcal{F}_\beta$, a decomposable metric that builds on two pillars. The first is the principle of meaning preservation $\mathcal{M}$: it measures to what extent a given AMR can be reconstructed from the generated sentence using SOTA AMR parsers and applying (fine-grained) AMR evaluation metrics to measure the distance between the original and the reconstructed AMR. The second pillar builds on a principle of (grammatical) form $\mathcal{F}$ that measures the linguistic quality of the generated text, which we implement using SOTA language models. In two extensive pilot studies we show that fulfillment of both principles offers benefits for AMR-to-text evaluation, including explainability of scores. Since $\mathcal{M}\mathcal{F}_\beta$ does not necessarily rely on gold AMRs, it may extend to other text generation tasks.