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 1709.04849cs.CL
收藏

神经机器翻译的自注意残差解码器

Self-Attentive Residual Decoder for Neural Machine Translation

École polytechnique fédérale de Lausanne (EPFL)(洛桑联邦理工学院);Idiap Research Institute(Idiap研究所);HEIG-VD / HES-SO(瑞士西部高等专业学院沃州工程师管理学院/瑞士西部高等专业学院)

Lesly Miculicich Werlen, Nikolaos Pappas, Dhananjay Ram, Andrei Popescu-Belis

摘要:

具有注意力的神经序列到序列网络在机器翻译中取得了显著的性能。其有效性的原因之一是它们能够通过注意力机制在每个时间步预测中捕获相关的源侧上下文信息。然而,目标端上下文仅基于序列模型,在实践中,该模型容易产生近因偏差,并且缺乏有效捕获单词之间的非顺序依赖关系的能力。为了解决这一限制,我们提出了一个目标侧关注的残差递归网络进行解码,其中对前一个单词的关注直接有助于下一个单词的预测。剩余学习促进了来自遥远过去的信息的流动,并且能够强调任何先前翻译的单词,因此它可以访问更广泛的上下文。所提出的模型优于神经MT基线以及记忆和自我注意力网络对三种语言。对解码器学习到的注意力的分析证实,它强调了更广泛的上下文,并且它捕获了类似句法的结构。

英文摘要:

Neural sequence-to-sequence networks with attention have achieved remarkable performance for machine translation. One of the reasons for their effectiveness is their ability to capture relevant source-side contextual information at each time-step prediction through an attention mechanism. However, the target-side context is solely based on the sequence model which, in practice, is prone to a recency bias and lacks the ability to capture effectively non-sequential dependencies among words. To address this limitation, we propose a target-side-attentive residual recurrent network for decoding, where attention over previous words contributes directly to the prediction of the next word. The residual learning facilitates the flow of information from the distant past and is able to emphasize any of the previously translated words, hence it gains access to a wider context. The proposed model outperforms a neural MT baseline as well as a memory and self-attention network on three language pairs. The analysis of the attention learned by the decoder confirms that it emphasizes a wider context, and that it captures syntactic-like structures.

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。

↑