论文标题
通过交替冻结特定语言的编码器来训练多语言机器翻译
Training Multilingual Machine Translation by Alternately Freezing Language-Specific Encoders-Decoders
论文作者
论文摘要
我们提出了一种特定于语言的编码器描述器的模块化体系结构，该体系结构构成了多语言的机器翻译系统，该系统可以逐步扩展到新语言，而无需在添加新语言时重新训练现有系统。与以前的作品不同，我们通过交替冻结编码器或解码器模块同时在所有翻译方向上训练$ n $语言，这间接迫使系统训练所有语言的通用中间表示。多语言机器翻译的实验结果表明，我们可以成功地训练这种模块化体系结构，以改善初始语言，同时在添加新语言或进行零拍译本时略微落后。在自然语言推理任务中句子表示质量的附加比较表明，交替的冻结训练在这个方向上也是有益的。
We propose a modular architecture of language-specific encoder-decoders that constitutes a multilingual machine translation system that can be incrementally extended to new languages without the need for retraining the existing system when adding new languages. Differently from previous works, we simultaneously train $N$ languages in all translation directions by alternately freezing encoder or decoder modules, which indirectly forces the system to train in a common intermediate representation for all languages. Experimental results from multilingual machine translation show that we can successfully train this modular architecture improving on the initial languages while falling slightly behind when adding new languages or doing zero-shot translation. Additional comparison of the quality of sentence representation in the task of natural language inference shows that the alternately freezing training is also beneficial in this direction.
