Log In Sign Up

Beyond English-Centric Multilingual Machine Translation

by   Angela Fan, et al.

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.


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

Existing multilingual machine translation approaches mainly focus on Eng...

A High-Quality Multilingual Dataset for Structured Documentation Translation

This paper presents a high-quality multilingual dataset for the document...

Facebook AI WMT21 News Translation Task Submission

We describe Facebook's multilingual model submission to the WMT2021 shar...

Multilingual Argument Mining: Datasets and Analysis

The growing interest in argument mining and computational argumentation ...

Learning to Translate for Multilingual Question Answering

In multilingual question answering, either the question needs to be tran...

Human Languages in Source Code: Auto-Translation for Localized Instruction

Computer science education has promised open access around the world, bu...

A Multilingual Neural Machine Translation Model for Biomedical Data

We release a multilingual neural machine translation model, which can be...

Code Repositories


We modify the M2M-100(Facebook) MLP layers by fastmoe

view repo