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 2004.03818cs.CLcs.LG
收藏

神经机器翻译的显式重排序

Explicit Reordering for Neural Machine Translation

National Institute of Information and Communications Technology (NICT)(信息通信研究机构(NICT))

Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita

摘要:

在基于transformer的神经机器翻译(NMT)中,位置编码机制帮助自注意网络学习具有顺序依赖性的源表示,使得基于transformer的NMT在各种翻译任务中都能获得最佳的结果。然而,基于变换器的NMT仅将位置的表示顺序地添加到输入句子中的词向量,并且没有显式地考虑该句子中的重排序信息。本文首先实证研究了源语重排信息与翻译效果之间的关系。实验结果表明,从双语并行数据集学习的目标顺序的源输入可以大大提高翻译性能。因此,我们提出了一种新的重排序方法来明确地为基于变换器的NMT建模这种重排序信息。在WMT 14英-德、WAT ASPEC日-英和WMT 17中-英翻译任务上的实验结果表明了该方法的有效性。

英文摘要:

In Transformer-based neural machine translation (NMT), the positional encoding mechanism helps the self-attention networks to learn the source representation with order dependency, which makes the Transformer-based NMT achieve state-of-the-art results for various translation tasks. However, Transformer-based NMT only adds representations of positions sequentially to word vectors in the input sentence and does not explicitly consider reordering information in this sentence. In this paper, we first empirically investigate the relationship between source reordering information and translation performance. The empirical findings show that the source input with the target order learned from the bilingual parallel dataset can substantially improve translation performance. Thus, we propose a novel reordering method to explicitly model this reordering information for the Transformer-based NMT. The empirical results on the WMT14 English-to-German, WAT ASPEC Japanese-to-English, and WMT17 Chinese-to-English translation tasks show the effectiveness of the proposed approach.

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。

↑