arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.01396cs.CL
收藏

语言建模、词汇翻译、重新排序:从经典SMT的视角看NMT的训练过程

Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT

University of Edinburgh(爱丁堡大学);University of Amsterdam(阿姆斯特丹大学);University of Zurich(苏黎世大学)

Elena Voita, Rico Sennrich, Ivan Titov

摘要:

与传统的统计机器翻译将翻译任务分解为不同的独立学习组件不同,神经机器翻译使用单个神经网络来建模整个翻译过程。尽管神经机器翻译是事实标准,但仍然不清楚NMT模型如何在训练过程中获得不同的能力,以及这如何反映传统SMT中的不同模型。在这项工作中,我们研究了与三个核心SMT组件相关的能力,并发现在培训过程中,NMT首先专注于学习目标端语言建模,然后提高翻译质量,接近逐字翻译,最后学习更复杂的重新排序模式。我们表明,这种行为适用于几个模型和语言对。此外,我们解释了这种对训练过程的理解在实践中是如何有用的,并作为一个例子,展示了如何通过指导教师模型选择来改进香草非自回归神经机器翻译。

英文摘要:

Differently from the traditional statistical MT that decomposes the translation task into distinct separately learned components, neural machine translation uses a single neural network to model the entire translation process. Despite neural machine translation being de-facto standard, it is still not clear how NMT models acquire different competences over the course of training, and how this mirrors the different models in traditional SMT. In this work, we look at the competences related to three core SMT components and find that during training, NMT first focuses on learning target-side language modeling, then improves translation quality approaching word-by-word translation, and finally learns more complicated reordering patterns. We show that this behavior holds for several models and language pairs. Additionally, we explain how such an understanding of the training process can be useful in practice and, as an example, show how it can be used to improve vanilla non-autoregressive neural machine translation by guiding teacher model selection.

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。

↑