Unsupervised Lexical Simplification with Context Augmentation

Takashi Wada, Timothy Baldwin, Jey Han Lau

Submission Type: Regular Short Paper

Submission Track: Semantics: Lexical

Keywords: lexical simplification, lexical substitution, lexical semantics, unsupervised

TL;DR: We propose a new unsupervised lexical simplification method that uses only monolingual data and pre-trained language models.

Abstract: We propose a new unsupervised lexical simplification method that uses only monolingual data and pre-trained language models. Given a target word and its context, our method generates substitutes based on the target context and also additional contexts sampled from monolingual data. We conduct experiments in English, Portuguese, and Spanish on the TSAR-2022 shared task, and show that our model substantially outperforms other unsupervised systems across all languages. We also establish a new state-of-the-art by ensembling our model with GPT-3.5. Lastly, we evaluate our model on the SWORDS lexical substitution data set, achieving a state-of-the-art result.

Submission Number: 1535