DeepAI AI Chat
Log In Sign Up

Balancing Training for Multilingual Neural Machine Translation

by   Xinyi Wang, et al.
Carnegie Mellon University

When training multilingual machine translation (MT) models that can translate to/from multiple languages, we are faced with imbalanced training sets: some languages have much more training data than others. Standard practice is to up-sample less resourced languages to increase representation, and the degree of up-sampling has a large effect on the overall performance. In this paper, we propose a method that instead automatically learns how to weight training data through a data scorer that is optimized to maximize performance on all test languages. Experiments on two sets of languages under both one-to-many and many-to-one MT settings show our method not only consistently outperforms heuristic baselines in terms of average performance, but also offers flexible control over the performance of which languages are optimized.


page 1

page 2

page 3

page 4


University of Cape Town's WMT22 System: Multilingual Machine Translation for Southern African Languages

The paper describes the University of Cape Town's submission to the cons...

Improving Neural Machine Translation of Indigenous Languages with Multilingual Transfer Learning

Machine translation (MT) involving Indigenous languages, including those...

Can You Traducir This? Machine Translation for Code-Switched Input

Code-Switching (CSW) is a common phenomenon that occurs in multilingual ...

Distributionally Robust Multilingual Machine Translation

Multilingual neural machine translation (MNMT) learns to translate multi...

Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits

Training data for machine translation (MT) is often sourced from a multi...

A Correlational Encoder Decoder Architecture for Pivot Based Sequence Generation

Interlingua based Machine Translation (MT) aims to encode multiple langu...

Building Machine Translation Systems for the Next Thousand Languages

In this paper we share findings from our effort to build practical machi...