DeepAI AI Chat
Log In Sign Up

Rapid Adaptation of Neural Machine Translation to New Languages

by   Graham Neubig, et al.
Carnegie Mellon University

This paper examines the problem of adapting neural machine translation systems to new, low-resourced languages (LRLs) as effectively and rapidly as possible. We propose methods based on starting with massively multilingual "seed models", which can be trained ahead-of-time, and then continuing training on data related to the LRL. We contrast a number of strategies, leading to a novel, simple, yet effective method of "similar-language regularization", where we jointly train on both a LRL of interest and a similar high-resourced language to prevent over-fitting to small LRL data. Experiments demonstrate that massively multilingual models, even without any explicit adaptation, are surprisingly effective, achieving BLEU scores of up to 15.5 with no data from the LRL, and that the proposed similar-language regularization method improves over other adaptation methods by 1.7 BLEU points average over 4 LRL settings. Code to reproduce experiments at


page 1

page 2

page 3

page 4


Adapting Multilingual Neural Machine Translation to Unseen Languages

Multilingual Neural Machine Translation (MNMT) for low-resource language...

Learning Kernel-Smoothed Machine Translation with Retrieved Examples

How to effectively adapt neural machine translation (NMT) models accordi...

More Parameters? No Thanks!

This work studies the long-standing problems of model capacity and negat...

Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information

We investigate the following question for machine translation (MT): can ...

The TALP-UPC System for the WMT Similar Language Task: Statistical vs Neural Machine Translation

Although the problem of similar language translation has been an area of...

The VolcTrans System for WMT22 Multilingual Machine Translation Task

This report describes our VolcTrans system for the WMT22 shared task on ...

BPE-Dropout: Simple and Effective Subword Regularization

Subword segmentation is widely used to address the open vocabulary probl...