CLApr 14, 2020

Balancing Training for Multilingual Neural Machine Translation

arXiv:2004.06748v41039 citations
AI Analysis

This addresses data imbalance issues for researchers and practitioners in multilingual machine translation, offering a more effective alternative to standard up-sampling techniques.

The paper tackles the problem of imbalanced training data in multilingual machine translation by proposing a method that automatically learns to weight training data to maximize performance across all languages, achieving consistent improvements over heuristic baselines in both one-to-many and many-to-one settings.

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.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes