Beyond English-Centric Multilingual Machine Translation

Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky +12 more
10/21/2020
cs.CLcs.LG

Official code: facebookresearch/fairseq (32,213 stars, MIT, PyTorch, last commit 2025-09-30).

Abstract

Existing work in translation demonstrated the potential of massively multilingual machine translation by training a single model able to translate between any pair of languages. However, much of this work is English-Centric by training only on data which was translated from or to English. While this is supported by large sources of training data, it does not reflect translation needs worldwide. In this work, we create a true Many-to-Many multilingual translation model that can translate directly between any pair of 100 languages. We build and open source a training dataset that covers thousands of language directions with supervised data, created through large-scale mining. Then, we explore how to effectively increase model capacity through a combination of dense scaling and language-specific sparse parameters to create high quality models. Our focus on non-English-Centric models brings gains of more than 10 BLEU when directly translating between non-English directions while performing competitively to the best single systems of WMT. We open-source our scripts so that others may reproduce the data, evaluation, and final M2M-100 model.

View on arXivView PDF

Code Implementations(1)

facebookresearch/fairseqOfficial100%
PyTorchMIT

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

32,2136,667C++, LuaAug 29, 20171 years agoMIT
artificial-intelligencepythonpytorch

Similar Papers

BigTranslate: Augmenting Large Language Models with Multilingual Translation Capability over 100 Languages

92% match1 repo2272023

Contrastive Learning for Many-to-many Multilingual Neural Machine Translation

90% match1 repo1202021

Omnilingual MT: Machine Translation for 1,600 Languages

89% match2026

To Translate or Not to Translate: A Systematic Investigation of Translation-Based Cross-Lingual Transfer to Low-Resource Languages

88% match2023

Assessing Translation capabilities of Large Language Models involving English and Indian Languages

88% match2023

Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis

88% match1 repo362023

Cite this paper

@article{fan2020beyond,
  title  = {Beyond English-Centric Multilingual Machine Translation},
  author = {Angela Fan and Shruti Bhosale and Holger Schwenk and Zhiyi Ma and Ahmed El-Kishky and Siddharth Goyal and Mandeep Baines and Onur Celebi and Guillaume Wenzek and Vishrav Chaudhary and Naman Goyal and Tom Birch and Vitaliy Liptchinsky and Sergey Edunov and Edouard Grave and Michael Auli and Armand Joulin},
  year   = {2020},
  eprint = {2010.11125},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2010.11125}
}

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/2010.11125.svg)](https://codeofpaper.com/paper/2010.11125)

Discussion