# Paraphrase Generation as Zero-Shot Multilingual Translation: Disentangling Semantic Similarity from Lexical and Syntactic Diversity

arXiv: https://arxiv.org/abs/2008.04935 · HTML: https://mlsanity.com/paper/2008.04935/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2020.

## Built on by (most cited first, 30 of 35)

- [Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense](https://mlsanity.com/paper/2303.13408/) (2023)
- [COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability](https://mlsanity.com/paper/2402.08679/) (2024)
- [Embarrassingly Easy Document-Level MT Metrics: How to Convert Any Pretrained Metric Into a Document-Level Metric](https://mlsanity.com/paper/2209.13654/) (2022)
- [ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness](https://mlsanity.com/paper/2305.12947/) (2023)
- [X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale](https://mlsanity.com/paper/2410.03115/) (2024)
- [Uncertainty-Aware Machine Translation Evaluation](https://mlsanity.com/paper/2109.06352/) (2021)
- [A Shocking Amount of the Web is Machine Translated: Insights from Multi-Way Parallelism](https://mlsanity.com/paper/2401.05749/) (2024)
- [Quality Controlled Paraphrase Generation](https://mlsanity.com/paper/2203.10940/) (2022)
- [Improving Statistical Significance in Human Evaluation of Automatic Metrics via Soft Pairwise Accuracy](https://mlsanity.com/paper/2409.09598/) (2024)
- [Fine-Tuned Machine Translation Metrics Struggle in Unseen Domains](https://mlsanity.com/paper/2402.18747/) (2024)
- [Improving Paraphrase Detection with the Adversarial Paraphrasing Task](https://mlsanity.com/paper/2106.07691/) (2021)
- [Dubbing in Practice: A Large Scale Study of Human Localization With Insights for Automatic Dubbing](https://mlsanity.com/paper/2212.12137/) (2022)
- [Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation](https://mlsanity.com/paper/2401.06643/) (2024)
- [Learning to Paraphrase Sentences to Different Complexity Levels](https://mlsanity.com/paper/2308.02226/) (2023)
- [Has Machine Translation Evaluation Achieved Human Parity? The Human Reference and the Limits of Progress](https://mlsanity.com/paper/2506.19571/) (2025)
- [Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?](https://mlsanity.com/paper/2410.09644/) (2024)
- [LLMs vs Established Text Augmentation Techniques for Classification: When do the Benefits Outweight the Costs?](https://mlsanity.com/paper/2408.16502/) (2024)
- [Pushing Paraphrase Away from Original Sentence: A Multi-Round Paraphrase Generation Approach](https://mlsanity.com/paper/2109.01862/) (2021)
- [Regressive Ensemble for Machine Translation Quality Evaluation](https://mlsanity.com/paper/2109.07242/) (2021)
- [Exploring Diversity in Back Translation for Low-Resource Machine Translation](https://mlsanity.com/paper/2206.00564/) (2022)
- [Target-Side Augmentation for Document-Level Machine Translation](https://mlsanity.com/paper/2305.04505/) (2023)
- [Enhanced Coherence-Aware Network with Hierarchical Disentanglement for Aspect-Category Sentiment Analysis](https://mlsanity.com/paper/2403.10214/) (2024)
- [A survey of diversity quantification in natural language processing: The why, what, where and how](https://mlsanity.com/paper/2507.20858/) (2025)
- [Levenshtein Training for Word-level Quality Estimation](https://mlsanity.com/paper/2109.05611/) (2021)
- [Improving Isochronous Machine Translation with Target Factors and Auxiliary Counters](https://mlsanity.com/paper/2305.13204/) (2023)
- [Improving the Diversity of Unsupervised Paraphrasing with Embedding Outputs](https://mlsanity.com/paper/2110.13231/) (2021)
- [A Measure of the System Dependence of Automated Metrics](https://mlsanity.com/paper/2412.03152/) (2024)
- [Crowdsourcing Diverse Paraphrases for Training Task-oriented Bots](https://mlsanity.com/paper/2109.09420/) (2021)
- [Can Multilinguality benefit Non-autoregressive Machine Translation?](https://mlsanity.com/paper/2112.08570/) (2021)
- [Improving Metrics for Speech Translation](https://mlsanity.com/paper/2305.12918/) (2023)

## Abstract (arXiv)

Recent work has shown that a multilingual neural machine translation (NMT) model can be used to judge how well a sentence paraphrases another sentence in the same language (Thompson and Post, 2020); however, attempting to generate paraphrases from such a model using standard beam search produces trivial copies or near copies. We introduce a simple paraphrase generation algorithm which discourages the production of n-grams that are present in the input. Our approach enables paraphrase generation in many languages from a single multilingual NMT model. Furthermore, the amount of lexical diversity between the input and output can be controlled at generation time. We conduct a human evaluation to compare our method to a paraphraser trained on the large English synthetic paraphrase database ParaBank 2 (Hu et al., 2019c) and find that our method produces paraphrases that better preserve meaning and are more gramatical, for the same level of lexical diversity. Additional smaller human assessments demonstrate our approach also works in two non-English languages.