Learning Policies for Multilingual Training of Neural Machine Translation Systems

arxiv(2021)

引用 0|浏览4
暂无评分
摘要
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.
更多
查看译文
关键词
neural machine translation systems,multilingual training,learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要