Learning Policies for Multilingual Training of Neural Machine Translation Systems
Not on the map. Why?
Abstract (arXiv)
Low-resource Multilingual Neural Machine Translation (MNMT) is typically tasked with improving the translation performance on one or more language pairs with the aid of high-resource language pairs. In this paper, we propose two simple search based curricula -- orderings of the multilingual training data -- which help improve translation performance in conjunction with existing techniques such as fine-tuning. Additionally, we attempt to learn a curriculum for MNMT from scratch jointly with the training of the translation system with the aid of contextual multi-arm bandits. We show on the FLORES low-resource translation dataset that these learned curricula can provide better starting points for fine tuning and improve overall performance of the translation system.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 14 of its 27 references that are in the map. First posted on arXiv 11 Mar 2021.
Builds on
14 of 27 references.
References · 14
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
- 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 467
- 2019Massively Multilingual Neural Machine Translation in the Wild: Findings and Challengescited by 253
- 2019Massively Multilingual Neural Machine Translationcited by 246
- 2019Simple, Scalable Adaptation for Neural Machine Translationcited by 239
- 2016Transfer Learning for Low-Resource Neural Machine Translationcited by 188
- 2014Algorithms for multi-armed bandit problemscited by 63
- 2019The FLoRes Evaluation Datasets for Low-Resource Machine Translation: Nepali-English and Sinhala-Englishcited by 61
- 2019Curriculum Learning for Domain Adaptation in Neural Machine Translationcited by 59
- 2018An Empirical Exploration of Curriculum Learning for Neural Machine Translationcited by 58
- 2019Reinforcement Learning based Curriculum Optimization for Neural Machine Translationcited by 29
2 more
- 2016Fast Domain Adaptation for Neural Machine Translationcited by 28
- 2018Improving Zero-Shot Translation of Low-Resource Languagescited by 11
Built on by
Citing papers per year: 2025: 1.
1 paper.