ParaLS: Lexical Substitution via Pretrained Paraphraser

TL;DR

This paper introduces ParaLS, a lexical substitution method leveraging pretrained paraphrasers to generate contextually appropriate substitutes that better preserve sentence meaning, outperforming existing models.

Contribution

It proposes a novel approach using paraphrasers with specialized decoding strategies for improved lexical substitution performance.

Findings

Outperforms state-of-the-art LS methods on three benchmarks.

Uses paraphrasers to generate substitutes that maintain sentence meaning.

Introduces two decoding strategies focusing on target word variations.

Abstract

Lexical substitution (LS) aims at finding appropriate substitutes for a target word in a sentence. Recently, LS methods based on pretrained language models have made remarkable progress, generating potential substitutes for a target word through analysis of its contextual surroundings. However, these methods tend to overlook the preservation of the sentence's meaning when generating the substitutes. This study explores how to generate the substitute candidates from a paraphraser, as the generated paraphrases from a paraphraser contain variations in word choice and preserve the sentence's meaning. Since we cannot directly generate the substitutes via commonly used decoding strategies, we propose two simple decoding strategies that focus on the variations of the target word during decoding. Experimental results show that our methods outperform state-of-the-art LS methods based on pre-trained language models on three benchmarks.