arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.12950cs.CL
收藏

基于非自回归Transformer的序列间模型集成训练

Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer

eBay Inc.(eBay公司);RWTH Aachen University(亚琛工业大学)

Evgeniia Tokarchuk, Jan Rosendahl, Weiyue Wang, Pavel Petrushkov, Tomer Lancewicki, Shahram Khadivi, Hermann Ney

摘要:

复杂的自然语言应用程序,如语音翻译或枢轴翻译,传统上依赖于级联模型。然而,级联模型是众所周知的,是容易发生错误传播和模型差异的问题。此外,在常规级联系统中不可能使用端到端训练数据,这意味着不能使用最适合于任务的训练数据。以前的研究提出了几种综合端到端培训的方法来克服这些问题,但它们大多依赖于(合成或自然)三方数据。我们提出了一种基于非自回归Transformer的级联模型,该模型可以实现端到端的训练,而无需显式的中间表示。这种新的架构(i)避免了可能导致错误的不必要的早期决策,这些错误随后在整个级联模型中传播,以及(ii)直接利用端到端训练数据。我们对两个基于机器翻译的机器翻译任务进行了评估,即法语-德语和德语-捷克语。我们的实验结果表明,所提出的架构产生了超过2 BLEU的法国-德国的级联基线的改善。

英文摘要:

Complex natural language applications such as speech translation or pivot translation traditionally rely on cascaded models. However, cascaded models are known to be prone to error propagation and model discrepancy problems. Furthermore, there is no possibility of using end-to-end training data in conventional cascaded systems, meaning that the training data most suited for the task cannot be used. Previous studies suggested several approaches for integrated end-to-end training to overcome those problems, however they mostly rely on (synthetic or natural) three-way data. We propose a cascaded model based on the non-autoregressive Transformer that enables end-to-end training without the need for an explicit intermediate representation. This new architecture (i) avoids unnecessary early decisions that can cause errors which are then propagated throughout the cascaded models and (ii) utilizes the end-to-end training data directly. We conduct an evaluation on two pivot-based machine translation tasks, namely French-German and German-Czech. Our experimental results show that the proposed architecture yields an improvement of more than 2 BLEU for French-German over the cascaded baseline.

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。

↑