"Definition Modeling: To model definitions." Generating Definitions With Little to No Semantics

TL;DR

This paper questions the effectiveness of definition modeling as a semantic evaluation tool, showing that existing models rely more on formal similarities than true semantic understanding.

Contribution

It provides evidence that current definition modeling systems are insensitive to semantics and depend on superficial formal features, challenging their validity for semantic evaluation.

Findings

Models are insensitive to polysemy

Models rely on formal similarities

Task may not reflect true semantics

Abstract

Definition Modeling, the task of generating definitions, was first proposed as a means to evaluate the semantic quality of word embeddings-a coherent lexical semantic representations of a word in context should contain all the information necessary to generate its definition. The relative novelty of this task entails that we do not know which factors are actually relied upon by a Definition Modeling system. In this paper, we present evidence that the task may not involve as much semantics as one might expect: we show how an earlier model from the literature is both rather insensitive to semantic aspects such as explicit polysemy, as well as reliant on formal similarities between headwords and words occurring in its glosses, casting doubt on the validity of the task as a means to evaluate embeddings.