arXivDaily arXiv每日学术速递 周一至周五更新
看起来今天可以划水了
arXiv 1606.01792cs.CL
收藏

具有外部短语记忆的神经机器翻译

Neural Machine Translation with External Phrase Memory

The University of Hong Kong(香港大学);Noah’s Ark Lab, Huawei Technologies(华为技术诺亚方舟实验室)

Yaohua Tang, Fandong Meng, Zhengdong Lu, Hang Li, Philip L. H. Yu

摘要:

在本文中,我们提出了phraseNet,一个神经机器翻译与短语记忆存储短语对符号形式,从语料库中挖掘或由人类专家指定。对于任何给定的源句子,phraseNet扫描短语存储器以确定候选短语对,并相应地将标记信息集成到源句子的表示中。该解码器采用词生成组件和短语生成组件的混合,并采用专门设计的策略一次生成多个词的序列。PhraseNet不仅向将外部知识融入神经机器翻译迈出了一步,而且还努力扩展了递归神经网络的逐词生成机制。我们对汉英翻译的实证研究表明,在记忆中仔细选择短语表,phraseNet比通用神经机器翻译器产生3.45 BLEU的改进。

英文摘要:

In this paper, we propose phraseNet, a neural machine translator with a phrase memory which stores phrase pairs in symbolic form, mined from corpus or specified by human experts. For any given source sentence, phraseNet scans the phrase memory to determine the candidate phrase pairs and integrates tagging information in the representation of source sentence accordingly. The decoder utilizes a mixture of word-generating component and phrase-generating component, with a specifically designed strategy to generate a sequence of multiple words all at once. The phraseNet not only approaches one step towards incorporating external knowledge into neural machine translation, but also makes an effort to extend the word-by-word generation mechanism of recurrent neural network. Our empirical study on Chinese-to-English translation shows that, with carefully-chosen phrase table in memory, phraseNet yields 3.45 BLEU improvement over the generic neural machine translator.

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。

↑