Semantic Role Labeling Meets Definition Modeling: Using Natural Language to Describe Predicate-Argument Structures

TL;DR

This paper proposes a novel approach to Semantic Role Labeling that uses natural language definitions to describe predicate-argument structures, enhancing interpretability and flexibility without sacrificing performance.

Contribution

It introduces a definition-based formulation of SRL, moving away from discrete labels, and demonstrates its effectiveness across various SRL datasets and formats.

Findings

Comparable performance to traditional SRL models

Enhanced interpretability of predicate-argument descriptions

Flexible modeling approach applicable to multiple SRL styles

Abstract

One of the common traits of past and present approaches for Semantic Role Labeling (SRL) is that they rely upon discrete labels drawn from a predefined linguistic inventory to classify predicate senses and their arguments. However, we argue this need not be the case. In this paper, we present an approach that leverages Definition Modeling to introduce a generalized formulation of SRL as the task of describing predicate-argument structures using natural language definitions instead of discrete labels. Our novel formulation takes a first step towards placing interpretability and flexibility foremost, and yet our experiments and analyses on PropBank-style and FrameNet-style, dependency-based and span-based SRL also demonstrate that a flexible model with an interpretable output does not necessarily come at the expense of performance. We release our software for research purposes at https://github.com/SapienzaNLP/dsrl.