Unsupervised Lexical Substitution with Decontextualised Embeddings
This addresses the problem of generating diverse and accurate word substitutes for natural language processing tasks, with improvements in handling low-frequency words and reducing biases.
The paper tackles lexical substitution by proposing an unsupervised method that uses similarity between contextualized and decontextualized embeddings, achieving new state-of-the-art results in English and Italian without supervision.
We propose a new unsupervised method for lexical substitution using pre-trained language models. Compared to previous approaches that use the generative capability of language models to predict substitutes, our method retrieves substitutes based on the similarity of contextualised and decontextualised word embeddings, i.e. the average contextual representation of a word in multiple contexts. We conduct experiments in English and Italian, and show that our method substantially outperforms strong baselines and establishes a new state-of-the-art without any explicit supervision or fine-tuning. We further show that our method performs particularly well at predicting low-frequency substitutes, and also generates a diverse list of substitute candidates, reducing morphophonetic or morphosyntactic biases induced by article-noun agreement.