PriMeSRL-Eval: A Practical Quality Metric for Semantic Role Labeling Systems Evaluation

TL;DR

This paper introduces PriMeSRL, a new evaluation metric for semantic role labeling that accounts for error propagation, providing a more accurate assessment of model performance and changing the relative rankings of state-of-the-art models.

Contribution

The paper proposes PriMeSRL, a practical and stricter SRL evaluation metric that considers full error propagation, improving the accuracy of model performance assessment.

Findings

PriMeSRL significantly lowers the performance scores of existing SRL models.

Model rankings change when evaluated with PriMeSRL compared to traditional metrics.

PriMeSRL effectively penalizes actual failures in SRL models.

Abstract

Semantic role labeling (SRL) identifies the predicate-argument structure in a sentence. This task is usually accomplished in four steps: predicate identification, predicate sense disambiguation, argument identification, and argument classification. Errors introduced at one step propagate to later steps. Unfortunately, the existing SRL evaluation scripts do not consider the full effect of this error propagation aspect. They either evaluate arguments independent of predicate sense (CoNLL09) or do not evaluate predicate sense at all (CoNLL05), yielding an inaccurate SRL model performance on the argument classification task. In this paper, we address key practical issues with existing evaluation scripts and propose a more strict SRL evaluation metric PriMeSRL. We observe that by employing PriMeSRL, the quality evaluation of all SoTA SRL models drops significantly, and their relative rankings also change. We also show that PriMeSRLsuccessfully penalizes actual failures in SoTA SRL models.