论文标题
使用自然语言提示进行机器翻译
Using natural language prompts for machine translation
论文作者
论文摘要
我们探索自然语言提示来控制机器翻译模型产生的输出的各个方面。我们证明了自然语言提示使我们能够影响形式或输出的特定方言之类的属性。我们表明，使用语言名称控制多语言翻译模型的输出语言可以使看不见的语言对的积极转移。这可以解锁将其英语名称转化为在微调过程中看不见的语言的能力。我们研究了规模，预训练步骤的数量，微调中的语言数量以及语言相似性会影响这种现象。
We explore the use of natural language prompts for controlling various aspects of the outputs generated by machine translation models. We demonstrate that natural language prompts allow us to influence properties like formality or specific dialect of the output. We show that using language names to control the output language of multilingual translation models enables positive transfer for unseen language pairs. This unlocks the ability to translate into languages not seen during fine-tuning by using their English names. We investigate how scale, number of pre-training steps, number of languages in fine-tuning, and language similarity affect this phenomenon.
