# Unsupervised Pivot Translation for Distant Languages

arXiv: https://arxiv.org/abs/1906.02461 · HTML: https://mlsanity.com/paper/1906.02461/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2019.

## Built on by (most cited first, 9 of 9)

- [The Effect of Domain and Diacritics in Yor`ub'a-English Neural Machine Translation](https://mlsanity.com/paper/2103.08647/) (2021)
- [MTG: A Benchmark Suite for Multilingual Text Generation](https://mlsanity.com/paper/2108.07140/) (2021)
- [CROP: Zero-shot Cross-lingual Named Entity Recognition with Multilingual Labeled Sequence Translation](https://mlsanity.com/paper/2210.07022/) (2022)
- [A Survey on Low-Resource Neural Machine Translation](https://mlsanity.com/paper/2107.04239/) (2021)
- [Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction](https://mlsanity.com/paper/2306.06804/) (2023)
- [Integrating Unsupervised Data Generation into Self-Supervised Neural Machine Translation for Low-Resource Languages](https://mlsanity.com/paper/2107.08772/) (2021)
- [POMP: Probability-driven Meta-graph Prompter for LLMs in Low-resource Unsupervised Neural Machine Translation](https://mlsanity.com/paper/2401.05596/) (2024)
- [Improving Zero-shot Multilingual Neural Machine Translation for Low-Resource Languages](https://mlsanity.com/paper/2110.00712/) (2021)
- [Lius: Translation Model Based Instructional Lingustic Using Continual Instruction Tuning In Kupang Malay](https://mlsanity.com/paper/2606.11786/) (2026)

## Abstract (arXiv)

Unsupervised neural machine translation (NMT) has attracted a lot of attention recently. While state-of-the-art methods for unsupervised translation usually perform well between similar languages (e.g., English-German translation), they perform poorly between distant languages, because unsupervised alignment does not work well for distant languages. In this work, we introduce unsupervised pivot translation for distant languages, which translates a language to a distant language through multiple hops, and the unsupervised translation on each hop is relatively easier than the original direct translation. We propose a learning to route (LTR) method to choose the translation path between the source and target languages. LTR is trained on language pairs whose best translation path is available and is applied on the unseen language pairs for path selection. Experiments on 20 languages and 294 distant language pairs demonstrate the advantages of the unsupervised pivot translation for distant languages, as well as the effectiveness of the proposed LTR for path selection. Specifically, in the best case, LTR achieves an improvement of 5.58 BLEU points over the conventional direct unsupervised method.