Rapid Adaptation of Neural Machine Translation to New Languages

08/13/2018
by   Graham Neubig, et al.
0

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 https://github.com/neubig/rapid-adaptation

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/30/2019

Adapting Multilingual Neural Machine Translation to Unseen Languages

Multilingual Neural Machine Translation (MNMT) for low-resource language...
research
05/18/2023

On the Off-Target Problem of Zero-Shot Multilingual Neural Machine Translation

While multilingual neural machine translation has achieved great success...
research
09/21/2021

Learning Kernel-Smoothed Machine Translation with Retrieved Examples

How to effectively adapt neural machine translation (NMT) models accordi...
research
07/20/2021

More Parameters? No Thanks!

This work studies the long-standing problems of model capacity and negat...
research
08/03/2019

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...
research
03/27/2023

Bilex Rx: Lexical Data Augmentation for Massively Multilingual Machine Translation

Neural machine translation (NMT) has progressed rapidly over the past se...
research
10/15/2021

Alternative Input Signals Ease Transfer in Multilingual Machine Translation

Recent work in multilingual machine translation (MMT) has focused on the...

Please sign up or login with your details

Forgot password? Click here to reset