解耦多语言机器翻译中目标端迁移与正则化的作用
Disentangling the Roles of Target-Side Transfer and Regularization in Multilingual Machine Translation
AI总结：
本研究通过大规模实验，解耦了多语言机器翻译中目标端语言相似性和语料库规模对知识迁移的影响，并发现远距离语言可通过正则化作用提升翻译性能。
摘要：
多语言机器翻译（MMT）受益于不同语言对之间的知识迁移。然而，与多对一翻译相比，一对多翻译的改进仅是边际性的，有时甚至可忽略不计。这种性能差异引发了一个问题：在一对多机器翻译中，正迁移在目标端扮演了多大程度的角色。在本文中，我们进行了一项大规模研究，沿着两个维度（即语言相似性和语料库规模）变化辅助目标端语言，以展示知识迁移对主要语言对的动态影响。我们表明，语言相似的辅助目标语言展现出强大的正知识迁移能力。随着相似目标语言规模的增加，正迁移进一步增强，从而惠及主要语言对。同时，我们发现，即使正迁移能力极小，远距离的辅助目标语言也能意外地惠及主要语言对。除了迁移之外，我们表明远距离的辅助目标语言可以充当正则化器，通过增强泛化和模型推理校准来提升翻译性能。
英文摘要：
Multilingual Machine Translation (MMT) benefits from knowledge transfer across different language pairs. However, improvements in one-to-many translation compared to many-to-one translation are only marginal and sometimes even negligible. This performance discrepancy raises the question of to what extent positive transfer plays a role on the target-side for one-to-many MT. In this paper, we conduct a large-scale study that varies the auxiliary target side languages along two dimensions, i.e., linguistic similarity and corpus size, to show the dynamic impact of knowledge transfer on the main language pairs. We show that linguistically similar auxiliary target languages exhibit strong ability to transfer positive knowledge. With an increasing size of similar target languages, the positive transfer is further enhanced to benefit the main language pairs. Meanwhile, we find distant auxiliary target languages can also unexpectedly benefit main language pairs, even with minimal positive transfer ability. Apart from transfer, we show distant auxiliary target languages can act as a regularizer to benefit translation performance by enhancing the generalization and model inference calibration.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
