# When and Why is Unsupervised Neural Machine Translation Useless?

arXiv: https://arxiv.org/abs/2004.10581 · HTML: https://mlsanity.com/paper/2004.10581/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2020.

## Built on by (most cited first, 30 of 34)

- [Neural Machine Translation for Low-Resource Languages: A Survey](https://mlsanity.com/paper/2106.15115/) (2021)
- [Survey of Low-Resource Machine Translation](https://mlsanity.com/paper/2109.00486/) (2021)
- [The unreasonable effectiveness of few-shot learning for machine translation](https://mlsanity.com/paper/2302.01398/) (2023)
- [Towards the Next 1000 Languages in Multilingual Machine Translation: Exploring the Synergy Between Supervised and Self-Supervised Learning](https://mlsanity.com/paper/2201.03110/) (2022)
- [Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2104.08570/) (2021)
- [Towards Making the Most of Multilingual Pretraining for Zero-Shot Neural Machine Translation](https://mlsanity.com/paper/2110.08547/) (2021)
- [Towards Universality in Multilingual Text Rewriting](https://mlsanity.com/paper/2107.14749/) (2021)
- [IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces](https://mlsanity.com/paper/2210.05098/) (2022)
- [Summarising Historical Text in Modern Languages](https://mlsanity.com/paper/2101.10759/) (2021)
- [A Theory of Unsupervised Translation Motivated by Understanding Animal Communication](https://mlsanity.com/paper/2211.11081/) (2022)
- [Majority Voting with Bidirectional Pre-translation For Bitext Retrieval](https://mlsanity.com/paper/2103.06369/) (2021)
- ["Wikily" Supervised Neural Translation Tailored to Cross-Lingual Tasks](https://mlsanity.com/paper/2104.08384/) (2021)
- [Translating away Translationese without Parallel Data](https://mlsanity.com/paper/2310.18830/) (2023)
- [Unsupervised Machine Translation On Dravidian Languages](https://mlsanity.com/paper/2103.15877/) (2021)
- [Integrating Unsupervised Data Generation into Self-Supervised Neural Machine Translation for Low-Resource Languages](https://mlsanity.com/paper/2107.08772/) (2021)
- [Low-Resource Machine Translation Training Curriculum Fit for Low-Resource Languages](https://mlsanity.com/paper/2103.13272/) (2021)
- [Crosslingual Embeddings are Essential in UNMT for Distant Languages: An English to IndoAryan Case Study](https://mlsanity.com/paper/2106.04995/) (2021)
- [Multilingual Bidirectional Unsupervised Translation Through Multilingual Finetuning and Back-Translation](https://mlsanity.com/paper/2209.02821/) (2022)
- [GRI: Graph-based Relative Isomorphism of Word Embedding Spaces](https://mlsanity.com/paper/2310.12360/) (2023)
- [Cost-Effective Training in Low-Resource Neural Machine Translation](https://mlsanity.com/paper/2201.05700/) (2022)
- [Exploiting Social Media Content for Self-Supervised Style Transfer](https://mlsanity.com/paper/2205.08814/) (2022)
- [The Impact of Syntactic and Semantic Proximity on Machine Translation with Back-Translation](https://mlsanity.com/paper/2403.18031/) (2024)
- [Self-Learning for Zero Shot Neural Machine Translation](https://mlsanity.com/paper/2103.05951/) (2021)
- [Using Document Similarity Methods to create Parallel Datasets for Code Translation](https://mlsanity.com/paper/2110.05423/) (2021)
- [Domain Mismatch Doesn't Always Prevent Cross-Lingual Transfer Learning](https://mlsanity.com/paper/2211.16671/) (2022)
- [On the Copying Problem of Unsupervised NMT: A Training Schedule with a Language Discriminator Loss](https://mlsanity.com/paper/2305.17182/) (2023)
- [Pointer-Generator Networks for Low-Resource Machine Translation: Don't Copy That!](https://mlsanity.com/paper/2403.10963/) (2024)
- [Relevance-guided Neural Machine Translation](https://mlsanity.com/paper/2312.00214/) (2023)
- [An Empirical study of Unsupervised Neural Machine Translation: analyzing NMT output, model's behavior and sentences' contribution](https://mlsanity.com/paper/2312.12588/) (2023)
- [Decoupled Vocabulary Learning Enables Zero-Shot Translation from Unseen Languages](https://mlsanity.com/paper/2408.02290/) (2024)

## Abstract (arXiv)

This paper studies the practicality of the current state-of-the-art unsupervised methods in neural machine translation (NMT). In ten translation tasks with various data settings, we analyze the conditions under which the unsupervised methods fail to produce reasonable translations. We show that their performance is severely affected by linguistic dissimilarity and domain mismatch between source and target monolingual data. Such conditions are common for low-resource language pairs, where unsupervised learning works poorly. In all of our experiments, supervised and semi-supervised baselines with 50k-sentence bilingual data outperform the best unsupervised results. Our analyses pinpoint the limits of the current unsupervised NMT and also suggest immediate research directions.