中国机器翻译研究的机遇与挑战——第八届全国机器翻译研讨会总结与展望

随着统计方法逐渐成为机器翻译研究的主流,机器翻译系统评测的分值越来越高,人们对机器翻译的信心和期望逐渐增加,社会对机器翻译应用的需求也越来越大。然而,现有的机器翻译理论和方法在系统性能上提升的空间逐渐减小,而且距离用户实际需求仍有很长的路要走。那么,面对期望、面对需求,机器翻译之路应该如何走？为此,第八届全国机器翻译研讨会对当前机器翻译研究所面临的挑战和机遇进行了深入研讨。该文详细介绍了该次研讨会六个专题的讨论情况,对机器翻译研究面临的机遇和挑战进行了认真的分析和总结。     

互联网机器翻译

该文在回顾机器翻译发展的基础上,总结了主要的机器翻译方法,并主要阐述互联网机器翻译的特点及面临的挑战.面向互联网机器翻译的应用需求,并针对互联网资源具有海量、高噪声、时效性、稀疏的特点,提出了多策略混合翻译方法、资源挖掘和过滤以及分布式处理技术、领域自适应技术,针对数据稀疏论述枢轴语言技术和新语种快速部署技术;然后结合...     

汉英机器翻译中格式转换研究

格式在HNC理论中是指广义作用句各主语块位置的不同排列组合方式。由于主语块的排列方式在汉英两种语言中表达的差异,汉语句子翻译到英语时常常发生格式转换。格式转换是HNC机器翻译理论的一个重要内容,是机器翻译理论实践的基础和前提。以HNC机器翻译理论为指导,以真实文本的专利文献汉英句对为分析对象,研究专利机器翻译中汉英两种语言之间广义作用句的格式转换规律,制定了排除规则、识别规则和转换规则,对部分规则进行了人工评测,结果表明准确率能达到85%左右。     

机器翻译辅助开发平台的设计与实现

介绍了一个机器翻译辅助开发平台MTDevStudio中的部分关键技术,包括模型定义、句法树操作的实现、语料库规则提取与统计分析、翻译引擎的评测等,重点对基于规则的机器翻译的辅助开发实现进行了介绍。该平台有利于减少机器翻译过程中的大量重复性工作,使研究者致力于自然语言理解的核心理论研究。与其它辅助工具相比,该平台致力于集成机器翻译涉及到的全面工作,用户可以自定义机器翻译模型,可扩展性好,并由机器翻译专家实际参与使用、评价,取得了不错的效果。     

第10届全国机器翻译研讨会

CWMT 2014旨在为国内外机器翻译界同行提供一个交互平台,加强国内外同行的学术交流,召集各路专家学者针对机器翻译的理论方法、应用技术和评测活动等若干基本关键问题进行深入的研讨,为促进中国机器翻译事业的发展,起到积极的推动作用。有别于以往,本次会议特设2个专题讲座,将和与会者互动探讨机器翻译最炽热的研究论点,而大会专题论坛汇集顶尖领域专家向大家揭示机器翻译最前沿的蓝图,本会还邀请了国内外知名     

感受机器翻译之——光翻译系统Light 1.0

Light1.0(见图 1)是基于机器翻译技术的英汉机器翻译系统,由史晓东博士等多名专业人员共同开发。在它的帮助文件里,关于Light 1.0,有这样一段话:Light1.0肯定不是世界上翻译速度最快的、翻译质量最高的英汉机器翻译系统。关于世     

诠释机器翻译软件的新理念——访北京雅信诚软件技术有限公司总经理范者正

机器翻译起源于30年代,人们一直将自动翻译视为机器翻译系统设计的终极目标。由此,国内外相当一部分专家开始对自然语言的处理现状、理论基础和技术路线进行冷静地思考。一些学者认为自然语言处理至今尚未跨越“语义障碍”,它们酝酿着新的突破。目前,世界上不少国家在实用化翻译软件上已经走出了自动翻译瓶颈,并取得了良好的市场效果,如德国的TRADOS翻译软     

基于面向对象机制构造机器翻译系统词典类库

本文提出用面向对象理论来建立机器翻译词典基类的方法,成功地用一种通用的模式来实现机器翻译中各科电子词典的管理。新方法较大地提高了机器翻译系统的可靠性、可维护性与可重用性,并已在NHWIN中日－日中机器翻译系统中得到了很好的应用。     

基于神经网络学习的统计机器翻译分析

文章主要对基于神经网络学习的统计机器翻译的相关内容进行了分析,希望通过对机器翻译的概述、流程以及深度学习等相关内容的阐述与分析可以为相关研究提供理论支持.     

利用语句结构信息的机器翻译自动评测初探

机器翻译评测对机器翻译有着极其重要的意义,它对翻译系统性能的提高做出了很大的贡献,同时促进了机器翻译的发展.本文在HNC机器翻译策略的基础上,对翻译语料的句类转换和句式转换做了初步的研究,并利用句类转换和句式转换的理论,建立了基于句类信息的自动评测的打分机制.     

基于本体的专业机器翻译术语词典研究

在专业机器翻译系统的设计和实现中,要解决的一个关键问题是如何有效地组织面向不同专业领域的专业术语,以及如何根据当前所处理的文本选择相应的术语定义。本文首先分析现有专业机器翻译系统在术语词典组织和建设方面存在的主要问题,以及基于本体(Ontology)的领域知识概念体系的特点;其次,探讨面向专业机器翻译的术语词典研究的几个重要方面,包括通用领域本体的设计、专业术语的描述和向本体的映射、双语或多语MT专业词库的组织和应用等;最后,介绍我们初步已完成的工作,主要包括机器翻译专业领域分类系统设计、专业词典向专业分类系统的映射、ICS标准向专业领域分类系统的映射等。映射实验结果表明,专业领域分类系统对于机器翻译专业词典具有良好的覆盖性。     

物联网技术应用于质量技术监督业务的前景分析

物联网作为继计算机、互联网之后,世界信息化发展的第三次浪潮,已成为国家科技发展战略的重要组成部分。本文以陕西省质量技术监督系统的信息化发展现状为例,对于在质量技术监督业务中应用物联网技术的前景进行了分析。     

Acquisition of large lexicons for practical knowledge-based MT

Although knowledge-based MT systems have the potential to achieve high translation accuracy, each successful application system requires a large amount of hand-coded lexical knowledge. Systems like KBMT-89 and its descendents have demonstrated how knowledge-based translation can produce good results in technical domains with tractable domain semantics. Nevertheless, the magnitude of the development task for large-scale applications with tens of thousands of domain concepts precludes a purely hand-crafted approach. The current challenge for the next generation of knowledge-based MT systems is to utilize on-line textual resources and corpus analysis software in order to automate the most laborious aspects of the knowledge acquisition process. This partial automation can in turn maximize the productivity of human knowledge engineers and help to make large-scale applications of knowledge-based MT an viable approach. In this paper we discuss the corpus-based knowledge acquisition methodology used in KANT, a knowledge-based translation system for multilingual document production. This methodology can be generalized beyond the KANT interlingua approach for use with any system that requires similar kinds of knowledge.     

数字孪生与平行系统:发展现状、对比及展望

随着物联网、大数据、人工智能（Artificial intelligence,AI）等技术的发展,针对促进新一代信息技术与制造业深度融合、实现制造物理世界与信息世界交互与共融的需要,数字孪生和平行系统技术成为智能制造和复杂系统管理与控制领域研究的热点.本文对数字孪生和平行系统技术的基本概念、技术内涵、相关应用等进行了研究与总结,对比了两者之间的异同,并分析了两者的发展趋势,预期能够给复杂系统管理与控制领域的研究人员提供一定的参考和借鉴.     

Automated object design: the client-server case

As more enterprises move to client-server environments, object technology is gaining favour as a means of migrating legacy applications. The object paradigm is well suited for modeling real world business processes and has the flexibility to integrate emerging technologies. However, the most difficult aspect of object-oriented applications development is not programming but technical design. This article explores a methodology that formalizes and automates object-based technical design in the domain of information management systems     

The fetish of technique: methodology as a social defence

Methodology is a central issue in the theory and practise of information systems development. Structured methods, for instance, have been widely championed as providing a way of improving the quality of software systems. In this paper a case study is presented in which a mail order company made an attempt to implement a well-known methodology, Structured Systems Analysis and Design Methodology (SSADM). Far from facilitating the development process, SSADM encouraged a rigid and mechanical approach in which the methodology was applied in a ritualistic way which inhibited creative thinking. The argument is thus, that methodology, although its influence may be benign, has the potential to operate as a 'social defence', i.e. as a set of organizational rituals with the primary function of containing anxiety. The grandiose illusion of an all-powerful method allows practitioners to deny their feelings of impotence in the face of the daunting technical and political challenges of systems development. By withdrawing into this fantasy world the learning processes that are critical to the success of systems development are jeopardized. Methodology, whilst masquerading as the epitome of rationality, may thus operate as an irrational ritual, the enactment of which provides designers with a feeling of security and efficiency at the expense of real engagement with the task at hand.     

Self-assembling modular robotic structures

Cellular automata in the two-dimensional (2-D) world have been used to simulate self-replicating structures based on natural biological systems, evolution, and emergence. In self-replication, large structures consisting of multiple cells are programmed to make copies of themselves using the rule-based systems upon which the cellular automata are governed. Although cellular automata environments are computer-based tools for representing complex systems within a virtual world, the field of modular robotics partly came about as an attempt to create self-relocatable cuboids that could function as cellular automata in the three-dimensional (3-D) real world to create physical self-replicating systems. The application of cellular automata to 3-D real-world applications has resulted in lattice-type modular robotic systems. Lattice systems are cubical in nature, where each cube is a self-mobile unit that can move orthogonally to a vacant position by sliding along existing portions of structure. These lattice-type modular robotics systems have been used to study self-reconfigurability in the real world with autonomous elements.     

Evaluating MT for massive open online courses

This article reports a multifaceted comparison between statistical and neural machine translation (MT) systems that were developed for translation of data from massive open online courses (MOOCs). The study uses four language pairs: English to German, Greek, Portuguese, and Russian. Translation quality is evaluated using automatic metrics and human evaluation, carried out by professional translators. Results show that neural MT is preferred in side-by-side ranking, and is found to contain fewer overall errors. Results are less clear-cut for some error categories, and for temporal and technical post-editing effort. In addition, results are reported based on sentence length, showing advantages and disadvantages depending on the particular language pair and MT paradigm.     

MulTran多语言机器翻译系统实现的语言学基础

MulTran是一个以实用化为目标的多语言机器翻译系统。该系统的特点是以一个统一的翻译处理程序控制运行四个语言翻译系统。该系统的技术核心是多功能逻辑运算分析技术,该技术的实现是靠建立一系列的功能函数,而这些功能函数是建立在诸如线性、离散性、递归性、层次性等自然语言的特性的基础之上的。     

Using multiple edit distances to automatically grade outputs from Machine translation systems

This paper addresses the challenging problem of automatically evaluating output from machine translation (MT) systems that are subsystems of speech-to-speech MT (SSMT) systems. Conventional automatic MT evaluation methods include BLEU, which MT researchers have frequently used. However, BLEU has two drawbacks in SSMT evaluation. First, BLEU assesses errors lightly at the beginning of translations and heavily in the middle, even though its assessments should be independent of position. Second, BLEU lacks tolerance in accepting colloquial sentences with small errors, although such errors do not prevent us from continuing an SSMT-mediated conversation. In this paper, the authors report a new evaluation method called "g Rader based on Edit Distances (RED)" that automatically grades each MT output by using a decision tree (DT). The DT is learned from training data that are encoded by using multiple edit distances, that is, normal edit distance (ED) defined by insertion, deletion, and replacement, as well as its extensions. The use of multiple edit distances allows more tolerance than either ED or BLEU. Each evaluated MT output is assigned a grade by using the DT. RED and BLEU were compared for the task of evaluating MT systems of varying quality on ATR's Basic Travel Expression Corpus (BTEC). Experimental results show that RED significantly outperforms BLEU.