WiC = TSV = WSD: On the Equivalence of Three Semantic Tasks

TL;DR

This paper demonstrates that WiC, WSD, and TSV are fundamentally equivalent semantic tasks, with practical reductions and empirical evidence supporting their interchangeability in NLP applications.

Contribution

It establishes the theoretical and empirical equivalence of WiC, WSD, and TSV, unifying these tasks under a common framework.

Findings

The three tasks can be pairwise reduced to each other.

Empirical results support the theoretical reductions.

Systems and datasets for WiC and WSD are compatible with the reductions.

Abstract

The Word-in-Context (WiC) task has attracted considerable attention in the NLP community, as demonstrated by the popularity of the recent MCL-WiC SemEval shared task. Systems and lexical resources from word sense disambiguation (WSD) are often used for the WiC task and WiC dataset construction. In this paper, we establish the exact relationship between WiC and WSD, as well as the related task of target sense verification (TSV). Building upon a novel hypothesis on the equivalence of sense and meaning distinctions, we demonstrate through the application of tools from theoretical computer science that these three semantic classification problems can be pairwise reduced to each other, and therefore are equivalent. The results of experiments that involve systems and datasets for both WiC and WSD provide strong empirical evidence that our problem reductions work in practice.