paper-with-me

홈 › Papers

Balancing Training for Multilingual Neural Machine Translation

2020-04-14 · ACL 2020 6 · Xinyi Wang, Yulia Tsvetkov, Graham Neubig

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.

📄 PDF Abstract BibTeX arXiv:2004.06748

Code (2)

cindyxinyiwang/multiDDS 공식 구현 pytorch
cindyxinyiwang/DataSelection pytorch

Tasks

Machine TranslationTranslation

Similar Papers 제목 키워드 기반

Competence-based Curriculum Learning for Multilingual Machine Translation

2021-09-09 · Findings (EMNLP) 2021 11 · Mingliang Zhang, Fandong Meng, Yunhai Tong, Jie zhou

Currently, multilingual machine translation is receiving more and more attention since it brings better performance for low resource languages (LRLs) and saves more space. However, existing multilingual machine translati…

Machine TranslationTranslation

Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training

2021-09-06 · EMNLP 2021 11 · Minghao Wu, Yitong Li, Meng Zhang, Liangyou Li 외

Learning multilingual and multi-domain translation model is challenging as the heterogeneous and imbalanced data make the model converge inconsistently over different corpora in real world. One common practice is to adju…

Machine TranslationTranslation

Causes and Cures for Interference in Multilingual Translation

2022-12-14 · Uri Shaham, Maha Elbayad, Vedanuj Goswami, Omer Levy 외

Multilingual machine translation models can benefit from synergy between different language pairs, but also suffer from interference. While there is a growing number of sophisticated methods that aim to eliminate interfe…

Machine TranslationTranslation

Towards Higher Pareto Frontier in Multilingual Machine Translation

2023-05-25 · Yichong Huang, Xiaocheng Feng, Xinwei Geng, Baohang Li 외

Multilingual neural machine translation has witnessed remarkable progress in recent years. However, the long-tailed distribution of multilingual corpora poses a challenge of Pareto optimization, i.e., optimizing for some…

Knowledge DistillationMachine TranslationTranslation

Scaling Laws for Multilingual Neural Machine Translation

2023-02-19 · Patrick Fernandes, Behrooz Ghorbani, Xavier Garcia, Markus Freitag 외

In this work, we provide a large-scale empirical study of the scaling properties of multilingual neural machine translation models. We examine how increases in the model size affect the model performance and investigate …

Machine TranslationTranslation