ParaLS: Lexical Substitution via Pretrained Paraphraser
This work addresses the challenge of maintaining sentence meaning in lexical substitution for natural language processing applications, representing an incremental improvement over existing methods.
The paper tackles the problem of lexical substitution by using a pretrained paraphraser to generate substitute candidates that preserve sentence meaning, and it shows that their proposed decoding strategies outperform state-of-the-art methods on three benchmarks.
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.