Unsupervised Paraphrasing of Multiword Expressions

Takashi Wada, Yuji Matsumoto, Timothy Baldwin, Jey Han Lau
6/2/2023
cs.CLcs.AIcs.LG

No confident code implementation found for this paper.

Abstract

We propose an unsupervised approach to paraphrasing multiword expressions (MWEs) in context. Our model employs only monolingual corpus data and pre-trained language models (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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

CoAM: Corpus of All-Type Multiword Expressions

81% match2024

Multilingual Lexical Simplification via Paraphrase Generation

80% match1 repo32023

LAMPAT: Low-Rank Adaption for Multilingual Paraphrasing Using Adversarial Training

79% match1 repo12024

Vector-Quantized Prompt Learning for Paraphrase Generation

78% match2023

Romanian Multiword Expression Detection Using Multilingual Adversarial Training and Lateral Inhibition

78% match2023

Distilling Monolingual and Crosslingual Word-in-Context Representations

78% match2024

Cite this paper

@article{wada2023unsupervised,
  title  = {Unsupervised Paraphrasing of Multiword Expressions},
  author = {Takashi Wada and Yuji Matsumoto and Timothy Baldwin and Jey Han Lau},
  year   = {2023},
  eprint = {2306.01443},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.01443v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.01443.svg)](https://codeofpaper.com/paper/2306.01443)

Discussion