# Unsupervised Paraphrasing without Translation

arXiv: https://arxiv.org/abs/1905.12752 · HTML: https://mlsanity.com/paper/1905.12752/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2019.

## Built on by (most cited first, 19 of 19)

- [Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense](https://mlsanity.com/paper/2303.13408/) (2023)
- [Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs](https://mlsanity.com/paper/2101.10579/) (2021)
- [Factorising Meaning and Form for Intent-Preserving Paraphrasing](https://mlsanity.com/paper/2105.15053/) (2021)
- [Hierarchical Sketch Induction for Paraphrase Generation](https://mlsanity.com/paper/2203.03463/) (2022)
- [LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning](https://mlsanity.com/paper/2305.18169/) (2023)
- [Unveiling Attractor Cycles in Large Language Models: A Dynamical Systems View of Successive Paraphrasing](https://mlsanity.com/paper/2502.15208/) (2025)
- [ConRPG: Paraphrase Generation using Contexts as Regularizer](https://mlsanity.com/paper/2109.00363/) (2021)
- [MOVER: Mask, Over-generate and Rank for Hyperbole Generation](https://mlsanity.com/paper/2109.07726/) (2021)
- [ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation](https://mlsanity.com/paper/2305.16585/) (2023)
- [Vector-Quantized Input-Contextualized Soft Prompts for Natural Language Understanding](https://mlsanity.com/paper/2205.11024/) (2022)
- [Principled Paraphrase Generation with Parallel Corpora](https://mlsanity.com/paper/2205.12213/) (2022)
- [Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning Representations](https://mlsanity.com/paper/2211.00881/) (2022)
- [Improving the Diversity of Unsupervised Paraphrasing with Embedding Outputs](https://mlsanity.com/paper/2110.13231/) (2021)
- [Dynamic User Interest Augmentation via Stream Clustering and Memory Networks in Large-Scale Recommender Systems](https://mlsanity.com/paper/2405.13238/) (2024)
- [Effective Unsupervised Constrained Text Generation based on Perturbed Masking](https://mlsanity.com/paper/2404.15877/) (2024)
- [ACCEPT: Adaptive Codebook for Composite and Efficient Prompt Tuning](https://mlsanity.com/paper/2410.12847/) (2024)
- [Paraphrase Generation as Unsupervised Machine Translation](https://mlsanity.com/paper/2109.02950/) (2021)
- [Action Controlled Paraphrasing](https://mlsanity.com/paper/2405.11277/) (2024)
- [Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder](https://mlsanity.com/paper/2506.20083/) (2025)

## Abstract (arXiv)

Paraphrasing exemplifies the ability to abstract semantic content from surface forms. Recent work on automatic paraphrasing is dominated by methods leveraging Machine Translation (MT) as an intermediate step. This contrasts with humans, who can paraphrase without being bilingual. This work proposes to learn paraphrasing models from an unlabeled monolingual corpus only. To that end, we propose a residual variant of vector-quantized variational auto-encoder. We compare with MT-based approaches on paraphrase identification, generation, and training augmentation. Monolingual paraphrasing outperforms unsupervised translation in all settings. Comparisons with supervised translation are more mixed: monolingual paraphrasing is interesting for identification and augmentation; supervised translation is superior for generation.