Lexical Substitution is not Synonym Substitution: On the Importance of Producing Contextually Relevant Word Substitutes

TL;DR

This paper introduces ConCat, a method that improves lexical substitution by leveraging context with pre-trained language models, leading to more relevant word replacements and highlighting issues in current benchmark evaluations.

Contribution

We propose ConCat, an augmented approach that enhances contextual relevance in lexical substitution using sentence information with pre-trained models.

Findings

ConCat outperforms existing methods in producing contextually relevant substitutes.

Human evaluators prefer ConCat's substitutions over previous approaches.

Analysis of CoInCo benchmark reveals limitations in current evaluation methods.

Abstract

Lexical Substitution is the task of replacing a single word in a sentence with a similar one. This should ideally be one that is not necessarily only synonymous, but also fits well into the surrounding context of the target word, while preserving the sentence's grammatical structure. Recent advances in Lexical Substitution have leveraged the masked token prediction task of Pre-trained Language Models to generate replacements for a given word in a sentence. With this technique, we introduce ConCat, a simple augmented approach which utilizes the original sentence to bolster contextual information sent to the model. Compared to existing approaches, it proves to be very effective in guiding the model to make contextually relevant predictions for the target word. Our study includes a quantitative evaluation, measured via sentence similarity and task performance. In addition, we conduct a qualitative human analysis to validate that users prefer the substitutions proposed by our method, as opposed to previous methods. Finally, we test our approach on the prevailing benchmark for Lexical Substitution, CoInCo, revealing potential pitfalls of the benchmark. These insights serve as the foundation for a critical discussion on the way in which Lexical Substitution is evaluated.