Hybrid Architectures for Machine Translation Systems

Although some progress has been made on the quality of Machine Translation in recent years, there is still a significant potential for quality improvement. There has also been a shift in paradigm of machine translation, from “classical” rule-based systems like METAL or LMT¹ towards example-based or statistical MT.² It seems to be time now to evaluate the progress and compare the results of these efforts, and draw conclusions for further improvements of MT quality.The paper starts with a comparison between statistical MT (henceforth: SMT) and rule-based MT (henceforth: RMT) systems, and describes the set-up and the evaluation results; the second section analyses the strengths and weaknesses of the respective approaches, and the third one discusses models of an architecture for a hybrid system.     

面向篇章机器翻译的英汉翻译单位和翻译模型研究

篇章机器翻译的首要问题是确定翻译单位。基于汉语和英语的语言知识和英汉翻译的实践,该文提出面向篇章机器翻译的基本单位和复合单位的双层单位体系,讨论了这两种单位支持篇章翻译应满足的性质,并据此勾画了篇章机器翻译的拆分、翻译、装配三步模型(PTA模型)。该文提出,汉语篇章机器翻译的复合单位为广义话题结构对应的文本块,基本单位则是根据广义话题结构流水模型得到的话题自足句;英语篇章机器翻译的复合单位为句号句,基本单位为naming-telling小句(NT小句),即指称性成分加上对它的陈述或后修饰成分所构成的小句。该文展示了在这样的翻译单位体系下采用PTA模型的英汉翻译过程实例,规划了面向篇章翻译的英汉小句对齐语料库的建设任务,讨论了PTA模型的可行性。
     

A Methodology for a Semi-Automatic Evaluation of the Lexicons of Machine Translation Systems

The lexicon is a major part of any Machine Translation (MT) system. If the lexicon of an MT system is not adequate, this will affect the quality of the whole system. Building a comprehensive lexicon, i.e., one with a high lexical coverage, is a major activity in the process of developing a good MT system. As such, the evaluation of the lexicon of an MT system is clearly a pivotal issue for the process of evaluating MT systems. In this paper, we introduce a new methodology that was devised to enable developers and users of MT Systems to evaluate their lexicons semi-automatically. This new methodology is based on the idea of the importance of a specific word or, more precisely, word sense, to a given application domain. This importance, or weight, determines how the presence of such a word in, or its absence from, the lexicon affects the MT system's lexical quality, which in turn will naturally affect the overall output quality. The method, which adopts a black-box approach to evaluation, was implemented and applied to evaluating the lexicons of three commercialEnglish–Arabic MT systems. A specific domain was chosen in which the various word-sense weights were determined by feeding sample texts from the domain into a system developed specifically for that purpose. Once this database of word senses and weights was built, test suites were presented to each of the MT systems under evaluation and their output rated by a human operator as either correct or incorrect. Based on this rating, an overall automated evaluation of the lexicons of the systems was deduced.     

基于多覆盖模型的神经机器翻译

覆盖模型可以缓解神经机器翻译中的过度翻译和漏翻译问题.现有方法通常依靠覆盖向量或覆盖分数等单一方式存储覆盖信息,而未考虑不同覆盖信息之间的关联性,因此对信息的利用并不完善.针对该问题,基于翻译历史信息的一致性和模型之间的互补性,提出了多覆盖融合模型.首先定义词级覆盖分数概念;然后利用覆盖向量和覆盖分数存储的信息同时指导...     

A Methodology for Evaluating Arabic Machine Translation Systems

This paper presents a methodology for evaluating Arabic Machine Translation (MT) systems. We are specifically interested in evaluating lexical coverage, grammatical coverage, semantic correctness and pronoun resolution correctness. The methodology presented is statistical and is based on earlier work on evaluating MT lexicons in which the idea of the importance of a specific word sense to a given application domain and how its presence or absence in the lexicon affects the MT system’s lexical quality, which in turn will affect the overall system output quality. The same idea is used in this paper and generalized so as to apply to grammatical coverage, semantic correctness and correctness of pronoun resolution. The approach adopted in this paper has been implemented and applied to evaluating four English-Arabic commercial MT systems. The results of the evaluation of these systems are presented for the domain of the Internet and Arabization.     

统计机器翻译中翻译模型的约简概述

统计机器翻译从诞生至今获得了长足的发展,目前已经成为机器翻译的主流.但是作为基础模块之一的翻译模型却随训练语料的增大而呈现飞速增大的趋势.为了使统计机器翻译更加实用,翻译模型的约简一直是研究热点之一.概述了统计机器翻译中翻译模型约简的研究现状,相关方法主要围绕解码过程统计分析、训练语料中的统计分析、翻译模型中的短语对自身特点分析等三个类别.结合相关分析,最后也探讨了这个方向的未来发展趋势.     

Optimizing Non-Decomposable Evaluation Metrics for Neural Machine Translation

While optimizing model parameters with respect to evaluation metrics has recently proven to benefit end to-end neural machine translation (NMT), the evaluation metrics used in the training are restricted to be defined at the sentence level to facilitate online learning algorithms. This is undesirable because the final evaluation metrics used in the testing phase are usually non-decomposable (i.e., they are defined at the corpus level and cannot be expressed as the sum of sentence-level metrics). To minimize the discrepancy between the training and the testing, we propose to extend the minimum risk training (MRT) algorithm to take non-decomposable corpus-level evaluation metrics into consideration while still keeping the advantages of online training. This can be done by calculating corpus-level evaluation metrics on a subset of training data at each step in online training. Experiments on Chinese-English and English-French translation show that our approach improves the correlation between training and testing and significantly outperforms the MRT algorithm using decomposable evaluation metrics.     

改进机器翻译中的句子切分模型

随着统计机器翻译系统训练语料的不断增加,长句子的数量越来越多,如何有效地利用长句子中的信息改进翻译质量是统计机器翻译系统面临的主要问题之一。该文基于Xu的句子切分模型,提出了一种在训练阶段切分长句子的方法,该方法利用自动获取的边界词概率和切分后子句对的长度比例来指导切分过程,从而得到更符合语义信息的句子切分结果。在NIST测试集上的实验结果表明,该方法获得了最大0.5个BLEU值的提升。     

Principles of Context-Based Machine Translation Evaluation

This article defines a Framework for Machine Translation Evaluation( FEMTI) which relates the quality model used to evaluate a machinetranslation system to the purpose and context of the system. Ourproposal attempts to put together, into a coherent picture, previousattempts to structure a domain characterised by overall complexity andlocal difficulties. In this article, we first summarise theseattempts, then present an overview of the ISO/IEC guidelines forsoftware evaluation (ISO/IEC 9126 and ISO/IEC 14598). As anapplication of these guidelines to machine translation software, weintroduce FEMTI, a framework that is made of two interrelatedclassifications or taxonomies. The first classification enablesevaluators to define an intended context of use, while the links tothe second classification generate a relevant quality model (qualitycharacteristics and metrics) for the respective context. The secondclassification provides definitions of various metrics used bythe community. Further on, as part of ongoing, long-term research, weexplain how metrics are analyzed, first from the general pointof view of meta-evaluation, then focusing on examples. Finally, weshow how consensus towards the present framework is sought for, andhow feedback from the community is taken into account in the FEMTIlife-cycle.     

机器翻译评测中的模糊匹配

目前,大多数机器翻译自动评测方法都没有考虑在未匹配的词语中可能包含被忽略的信息。本文提出一种在参考译文和待评测译文之间自动搜索模糊匹配词对的方法,并给出相似度的计算方法。模糊匹配和计算相似度的整个过程将通过一个例子进行说明。实验表明,我们的方法能够较好地找到被忽略的、有意义的词对。更重要的是,通过引入模糊匹配,BLEU 的性能得到显著的提高。模糊匹配可以用来提高其他机器翻译自动评测方法的性能。     

中文全词消歧在机器翻译系统中的性能评测

独立的词义消歧模型性能已经获得很大提高, 但是对于独立消歧模型在机器翻译系统中应用的必要性和作用一直存在着不同的观点. 为了从更为一般性的角度评价这个问题, 本文突破了具体模型的限制, 通过在不同类型汉英机器翻译系统中引入不受特定条件约束的高精度全词消歧过程, 对词义消歧在机器翻译系统中的影响进行了较为充分和全面的评价. 实验结果证明词义消歧模型不仅本身具有一定的翻译能力, 而且可以提高不同类型的机器翻译系统的整体性能. 同时也说明当前的翻译系统在消歧能力上还有较大的提升空间.     

基于非连续短语的统计翻译模型研究

目前统计机器翻译的主流方法仍然是基于短语的翻译模型。然而,该模型并没有考虑对非连续短语的处理。本文提出了一种基于非连续短语的统计翻译模型,利用该模型可以使翻译的基本单元从连续短语扩展到带有间隔的非连续短语,以更好地解决词语翻译时的上下文依赖问题。同时,由于该方法抽取的短语数量较少,也使得解码的效率得到了提高。实验表明,在效率提高的情况下,非连续短语模型可以取得与层次型短语模型相当的翻译结果。     

一种面向口语的译文质量自动评价方法

译文质量的自动评价对机器翻译研究具有十分重要的意义。但现有方法主要是针对书面语翻译,没有考虑到口语翻译的特征。因此,本文提出了一种面向口语的新型的自动评价方法,通过定义信息段、标注权重和设计多种匹配策略等方法,使自动评价结果与人工打分更为接近,同时也提高了评价过程对不同输出译文的适应能力。各项实验表明,该算法对译文质量变化具有较高的敏感度,而且可以对输出译文质量作出与手工评判较为接近的评价结果。     

机器翻译评测的新进展

机器翻译评测对机器翻译的研究和开发具有至关重要的作用,对其的研究一直是国内外机器翻译界的重点课题。本文首先全面地介绍了最近出现的而且受到极大关注的机器翻译评测技术,即IBM公司的BLEU机器翻译评测标准和NIST采用的机器翻译评测技术。实验表明,自动翻译评测技术能够接近人工评价,评测结果也是可接受的。因此,采用自动翻译评测技术能够给自然语言处理的研究人员和开发人员带来很大的便利性。本文还展示了一个开放式的可扩展的自动翻译评测的平台,完全实现了BLEU和NIST评测标准,并做出了一定的改进使得该系统具有良好的使用性和可扩展性。     

一种基于E-Chunk的机器翻译模型

提出了一种基于E-Chunk的多引擎机器翻译模型.该模型以中心语驱动的分析技术为基础,通过词汇相似特征计算E-Chunk的匹配代价,自底向上地完成最优E-Chunk覆盖的构造,并以E-Chunk为基本翻译单元完成机器翻译过程.初步的实验结果显示,该方法在面向领域文本的自动翻译方面是有效的.     

电网可靠性评估的PSO-SVR评估模型

城市电网结构复杂,数据量大是电网可靠性评估的难点,导致了传统的电网可靠性评估方法难以有效评估.为提高评估的精度和效率,提出一种基于粒子群支持向量回归法的电网可靠性评估的新方法解决电网可靠性评估的问题,采用供电可靠率作为评估指标,粒子群支持向量回归法能克服传统的人工神经网络可靠性评估方法易陷人局部极值.采用电网可靠性评估特征参数与评估指标,确定评估模型结构,再用粒子群优化算法优化支持向量回归模型参数.仿真结果表明,粒子群支持向量回归法可靠性评估精度高于人工神经网络.证明粒子群支持向量回归的电网可靠性评估方法具有更好的应用价值.     

机器翻译自动评价综述

随着机器翻译的发展,对其质量进行评测的自动评价方法也越来越受重视。发展至今,各种评价方法与技术层出不穷,采用何种分类标准来组织和描述它们也是一个很大的挑战。根据核心技术的不同,该文重点介绍了三类主流的自动评价方法,包括: 基于语言学检测点的方法、字符串匹配的方法和基于机器学习的方法。论文分别阐述了这些类别中颇具代表性的方法的工作原理并分析了各自的优缺点。此外,受限参考译文下的评价技术虽然不是主流的方法,但是其对提高自动化程度和评价性能的作用不能忽视,所以该文将其作为特殊的类别做了阐述。然后,汇报了近年来衡量自动评价方法的国际评测结果。最后,总结了自动评价的发展趋势和有待进一步解决的相关问题。     

基于Self-Attention模型的机器翻译系统

近几年来神经机器翻译（Neural Machine Translation, NMT）发展迅速，Seq2Seq框架的提出为机器翻译带来了很大的优势，可以在观测到整个输入句子后生成任意输出序列。但是该模型对于长距离信息的捕获能力仍有很大的局限，循环神经网络（RNN）、 LSTM网络都是为了改善这一问题提出的，但是效果并不明显。注意力机制的提出与运用则有效地弥补了该缺陷。Self-Attention模型就是在注意力机制的基础上提出的，本文使用Self-Attention为基础构建编码器-解码器框架。本文通过探讨以往的神经网络翻译模型，分析Self-Attention模型的机制与原理，通过TensorFlow深度学习框架对基于Self-Attention模型的翻译系统进行实现，在英文到中文的翻译实验中与以往的神经网络翻译模型进行对比，表明该模型取得了较好的翻译效果。     

基于句子相似度的机器翻译评价方法及其有效性分析

为了帮助开发面向本地化的基于实例的机器翻译(EBMT)系统,提出利用句子相似度评价译文质量的方法．该方法能够较有效地区分不同翻译质量的译文,从而帮助开发者发现EBMT系统存在的问题．为了证明该评价方法的有效性,对比了6个机器翻译系统人工评价和自动评价的结果．通过相关分析和显著性检验,表明了此方法和人工方法存在高度的一致性．最后提出在自动评价结果的基础上利用线性回归预测人工评分方法．     

机器翻译测评的实践与分析

机器翻译是人工智能领域中一项有挑战性的研究课题,而对机器翻译系统的测评也越来越受到重视。为了考察现今机器翻译系统的翻译质量及其出现的问题,提出了采用大规模语料库作为测试集的方法,对六个机器翻译系统进行了半自动测评,分析了机器翻译系统在词法和句法上存在的问题,并将测评结果与NIST自动测评进行比较,分析了测评结果的客观性。