2000 character limit reached
Unsupervised Paraphrasing of Multiword Expressions (2306.01443v1)
Published 2 Jun 2023 in cs.CL, cs.AI, and cs.LG
Abstract: We propose an unsupervised approach to paraphrasing multiword expressions (MWEs) in context. Our model employs only monolingual corpus data and pre-trained LLMs (without fine-tuning), and does not make use of any external resources such as dictionaries. We evaluate our method on the SemEval 2022 idiomatic semantic text similarity task, and show that it outperforms all unsupervised systems and rivals supervised systems.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.