神经机器翻译综述  

A Survey of Neural Machine Translation

作　　者：李亚超 熊德意[1] 张民[1] LI Ya-Chao;XIONG De-Yi;ZHANG Min(School of Computer Science and Technology,Soochow University,Suzhou,Jiangsu 215006;Key Laboratory of China＇s Ethnic Languages and Information Technology of Ministry of Education,Northwest Minzu University,Lanzhou 730030)

机构地区：[1]苏州大学计算机科学与技术学院,江苏苏州215006 [2]西北民族大学中国民族语言文字信息技术教育部重点实验室,兰州730030

出　　处：《计算机学报》2018年第12期2734-2755,共22页Chinese Journal of Computers

基　　金：国家自然科学基金(61525205;61432013;61403269);西北民族大学中央高校基本科研业务费专项资金资助项目(31920170154;31920170153);甘肃省高等学校科研项目(2016B-007)资助~~

摘　　要：机器翻译研究将源语言所表达的语义自动转换为目标语言的相同语义,是人工智能和自然语言处理的重要研究内容.近年来,基于序列到序列模型(Sequence-to-Sequence Model)形成一种新的机器翻译方法:神经机器翻译(Neural Machine Translation,NMT),它完全采用神经网络完成源语言到目标语言的翻译过程,成为一种极具潜力全新的机器翻译模型.神经机器翻译经过最近几年的发展,取得了丰富的研究成果,在多数语言对上逐渐超过了统计机器翻译方法.该文首先介绍了经典神经机器翻译模型及存在的问题与挑战;然后简单概括神经机器翻译中常用的神经网络;之后按照经典神经机器翻译模型、基础共性问题、新模型、新架构等分类体系详细介绍了相关研究进展;接着简单介绍基于神经网络的机器翻译评测方法;最后展望未来研究方向和发展趋势,并对该文做出总结.Machine translation is a subfield of artificial intelligence and natural language processing that investigates transforming the source language into the target language. Neural machine translation is a recently proposed framework for machine translation based purely on sequence - to-sequence models, in which a large neural network is used to transform the source language sequence into the target language sequence, leading to a novel paradigm for machine translation. After years of development, NMT has gained rich results and gradually surpassed the statistical machine translation （SMT method over various language pairs, becoming a new machine translation model with great potential. In this paper, we systematically describe the vanilla NMT model and the different types of NMT models according to the principles of classical NMT model, the common and shared problems of NMT model, the novel models and new architectures, and other classification systems. First, we introduce the Encoder-Decoder based NMT as well as the problems and challenges in the model. In the vanilla NMT model, the encoder, implemented by a recurrent neural network （RNN, reads an input sequence to produce a fixed-length vector, from which the decoder generates a sequence of target language words. The biggest issue in the vanilla NMT model is that a sentence of any length needs to be compressed into a fixed-length vector that may be losing important information of a sentence, which is a bottleneck in NMT. Next, we summarize the neural networks used in NMT, including RNNs, convolutional neural networks （CNN, long short-term memory （LSTM neural networks, gated recurrent neural networks, neural Turing machines （NTM, and memory networks, et al. Then, this paper introduces the current research situation of NMT in detail, including the attention-based NMT through attention mechanism, which is designed to predict the soft alignment between the source language and the target language, thus has greatly improved the performance of NMT; the character

关 键 词：机器翻译 神经机器翻译 注意力机制 循环神经网络 序列到序列模型 机器翻译评测 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]