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 1503.01838cs.CLcs.LGcs.NE
收藏

基于卷积神经网络的机器翻译源语言编码

Encoding Source Language with Convolutional Neural Network for Machine Translation

Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Noah’s Ark Lab, Huawei Technologies(华为技术诺亚方舟实验室);Dublin City University(都柏林城市大学)

Fandong Meng, Zhengdong Lu, Mingxuan Wang, Hang Li, Wenbin Jiang, Qun Liu

摘要:

最近提出的神经网络关节模型(NNJM)(Devlin等人,2014)通过精确选择的源上下文窗口增强了n-gram目标语言模型,从而在SMT中实现了最先进的性能。在本文中,我们通过由目标信息引导的卷积架构来总结相关的源信息,从而给出了一个更系统的处理。在解码过程中使用不同的引导信号,我们专门设计的卷积+门控架构可以精确定位源句子中与预测目标词相关的部分,并将它们与整个源句子的上下文融合,形成统一的表示。该表示与目标语言单词一起被馈送到深度神经网络(DNN)以形成更强的NNJM。在两个NIST汉英翻译任务上的实验结果表明,该模型比以往的NNJM模型平均提高了1.08个BLEU点

英文摘要:

The recently proposed neural network joint model (NNJM) (Devlin et al., 2014) augments the n-gram target language model with a heuristically chosen source context window, achieving state-of-the-art performance in SMT. In this paper, we give a more systematic treatment by summarizing the relevant source information through a convolutional architecture guided by the target information. With different guiding signals during decoding, our specifically designed convolution+gating architectures can pinpoint the parts of a source sentence that are relevant to predicting a target word, and fuse them with the context of entire source sentence to form a unified representation. This representation, together with target language words, are fed to a deep neural network (DNN) to form a stronger NNJM. Experiments on two NIST Chinese-English translation tasks show that the proposed model can achieve significant improvements over the previous NNJM by up to +1.08 BLEU points on average

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。

↑