Improving Phrase-Based Statistical Machine Translation Models by Incorporating Syntax-Based Language Models

This paper proposed a method to incorporate syntax-based language models in phrase-based statistical machine translation (SMT) systems. The syntax-based language model used in this paper is based on link grammar,which is a high lexical formalism. In order to apply language models based on link grammar in phrase-based models,the concept of linked phrases,an extension of the concept of traditional phrases in phrase-based models was brought out. Experiments were conducted and the results showed that the use of syntax-based language models could improve the performance of the phrase-based models greatly.

Korean Morphological Analysis for Korean-Vietnamese Statistical Machine Translation

This paper describes the experiments with Korean-to-Vietnamese statistical machine translation(SMT). The fact that Korean is a morphologically complex language that does not have clear optimal word boundaries causes a major problem of translating into or from Korean. To solve this problem, we present a method to conduct a Korean morphological analysis by using a pre-analyzed partial word-phrase dictionary(PWD).Besides, we build a Korean-Vietnamese parallel corpus for training SMT models by collecting text from multilingual magazines. Then, we apply such a morphology analysis to Korean sentences that are included in the collected parallel corpus as a preprocessing step. The experiment results demonstrate a remarkable improvement of Korean-to-Vietnamese translation quality in term of bi-lingual evaluation understudy(BLEU).

Graph-based Lexicalized Reordering Models for Statistical Machine Translation

Lexicalized reordering models are very important components of phrasebased translation systems.By examining the reordering relationships between adjacent phrases,conventional methods learn these models from the word aligned bilingual corpus,while ignoring the effect of the number of adjacent bilingual phrases.In this paper,we propose a method to take the number of adjacent phrases into account for better estimation of reordering models.Instead of just checking whether there is one phrase adjacent to a given phrase,our method firstly uses a compact structure named reordering graph to represent all phrase segmentations of a parallel sentence,then the effect of the adjacent phrase number can be quantified in a forward-backward fashion,and finally incorporated into the estimation of reordering models.Experimental results on the NIST Chinese-English and WMT French-Spanish data sets show that our approach significantly outperforms the baseline method.

RM-structure alignment based statistical machine translation model

A novel model based on structure alignments is proposed for statistical machine translation in thispaper.Meta-stnlcture and sequence of meta-structure for a parse tree are defined.During the translationprocess,a parse tree is decomposed to deal with the structure divergence and the alignments can be con-stmcted at different levels of recombination of meta-structure(RM).This method can perform the struc-ture mapping across the sub-tree structure between languages.As a result,we get not only the translationfor the target language,but sequence of meta-structure of its parse tree at the same time.Experimentsshow that the model in the framework of log-linear model has better generative ability and significantlyoutperforms Pharaoh,a phrase-based system.

Research on high-performance English translation based on topic model

Retelling extraction is an important branch of Natural Language Processing(NLP),and high-quality retelling resources are very helpful to improve the performance of machine translation.However,traditional methods based on the bilingual parallel corpus often ignore the document background in the process of retelling acquisition and application.In order to solve this problem,we introduce topic model information into the translation mode and propose a topic-based statistical machine translation method to improve the translation performance.In this method,Probabilistic Latent Semantic Analysis(PLSA)is used to obtains the co-occurrence relationship between words and documents by the hybrid matrix decomposition.Then we design a decoder to simplify the decoding process.Experiments show that the proposed method can effectively improve the accuracy of translation.

1951—2017年热带气旋移动速度特征统计分析

热带气旋移动速度是目前热带气旋研究热点之一。本文利用1951—2017年中国国家气象局最佳路径集资料,系统分析了西北太平洋海域热带气旋不同强度等级移动速度的年代际特征,初步探讨其原因,并对不同强度等级移动速度的分布特征进行系统诊断。结果表明,1951—2017年间平均移动速度(所有强度等级平均及对于大部分强度等级)呈现出减慢趋势,且主要体现在强热带气旋等级移动速度减慢;热带气旋向高纬度迁移趋势理论上将使移动速度增大而移动速度仍然减慢,说明气候因素是引起移动速度减慢的一个重要因素;不同强度等级平均移动速度、增强阶段基本相当,减弱阶段随强度减弱在初、中期明显增加,之后又逐渐减小,变性气旋移动速度显著增加;不同强度等级速度概率分布,增强阶段基本相同且相对集中,减弱阶段差异较大且相对分散,变性气旋最为分散。

维吾尔语机器翻译研究综述

维吾尔语机器翻译作为我国低资源机器翻译研究的重要任务之一,其发展与应用可以更好地促进不同地区和民族之间的文化交流与贸易往来。然而,维吾尔语作为一种黏着性语言,在机器翻译领域存在形态复杂、语料稀缺等问题。近年来,在维吾尔语机器翻译发展的不同阶段,研究人员针对其特点在算法和模型上不断优化与创新,取得了一定的研究成果,但缺乏系统性的综述。全面回顾维吾尔语机器翻译的相关研究,并根据方法的不同将其分为基于规则和实例的维吾尔语机器翻译、基于统计的维吾尔语机器翻译以及基于神经网络的维吾尔语机器翻译3种类型,同时对相关学术活动和语料库资源进行汇总。为进一步探索维吾尔语机器翻译的潜力,采用ChatGPT模型对维吾尔语-汉语机器翻译任务进行初步研究,实验结果表明,在Few-shot情景下,随着示例数的增加,翻译性能先升后降,在10-shot时表现最佳。此外,思维链方法在维吾尔语机器翻译任务中并未展示出更优的翻译能力。最后对维吾尔语机器翻译未来的研究方向进行了展望。

高分辨率人脸纹理图全流程生成方法

针对人脸纹理生成相关研究大部分聚焦于低分辨率纹理生成的问题,将图像翻译运用到高分辨率纹理图的生成中,提出一种以图像翻译网络为核心的1024×1024纹理图的全流程生成方法。在快速高效生成的同时,有效缓解了生成人脸UV纹理分辨率低的问题。在图像翻译网络中,由卷积神经网络作为骨干网络,嵌入统计纹理学习网络(STLNet),并采用软自适应层实例规范化(Soft-AdaLIN)的归一化方法共同构成生成器,同时采用多尺度判别来指导高分辨率纹理图像的生成,最后进行颜色转换与泊松融合完成纹理校正。在FFHQ数据集随机抽取图像并进行人脸归一化后进行测试,通过一系列评价指标进行定量评估、同近年相关研究方法进行定性及定量比较,验证了该全流程生成方法在生成1024×1024人脸UV纹理图像上的优势。

中华学术外译语言学项目统计分析及译传策略

中华学术外译承担着向世界传播中国声音的使命,已成为备受瞩目的国家级项目。但目前对项目的整体研究相对较少,尤其缺乏对具体学科门类的实证分析。通过对2010-2022年的立项信息的研究结果显示,语言学立项主题以汉语本体研究为主、立项文版分布不均衡、推荐选题数量有限、海外传播力度不足,因此,建立语言学撰写、出版、翻译和海外传播的外译联动机制,广泛选题,积极申报,平衡文版,以通过多维角度、多方渠道来推动中华学术外译的高效实施,为项目决策者和申请者提供重要参考。

A Substitution-Translation-Restoration Framework for Handling Unknown Words in Statistical Machine Translation

Unknown words are one of the key factors that greatly affect the translation quality. Traditionally, nearly all the related researches focus on obtaining the translation of the unknown words. However, these approaches have two disadvantages. On the one hand, they usually rely on many additional resources such as bilingual web data; on the other hand, they cannot guarantee good reordering and lexical selection of surrounding words. This paper gives a new perspective on handling unknown words in statistical machine translation （SMT）. Instead of making great efforts to find the translation of unknown words, we focus on determining the semantic function of the unknown word in the test sentence and keeping the semantic function unchanged in the translation process. In this way, unknown words can help the phrase reordering and lexical selection of their surrounding words even though they still remain untranslated. In order to determine the semantic function of an unknown word, we employ the distributional semantic model and the bidirectional language model. Extensive experiments on both phrase-based and linguistically syntax-based SMT models in Chinese-to-English translation show that our method can substantially improve the translation quality.

A Statistical Approach to Annotation in the English Translation of Chinese Classics:A Case Study of the Four English Versions of Fushengliuji

Annotation in translation is of great value in communicating"the local"to the global readership.Based on our content and function-centered statistics on the 483 notes of the four English versions of Shen Fu’s autobiographical work Fushengliuji,we find that 1)in terms of content,cultural,geographic,historical,and literary references are the most important categories of annotation in the English translation of this work;annotations in the four versions are employed to serve 6 major functions/purposes:to further inform,to facilitate understanding,to avoid misunderstanding,to interpret personally,to cite or allude,and to correct mistakes;2)no correlation can be established between the use of annotation and the reception of the work per se,but it can reflect the translator’s poise and strategy which ultimately affect the reception of the work;and 3)Lin’s version used relatively few notes and relied heavily on paraphrasing,a practice which leads to better accessibility of his translation and at the same time to the possible sacrifice of some culturally and socially significant elements of the original.Black’s translation used notes sparingly,and she was so creative as to rearrange and edit the original text,revealing her approach of radical"reader-centeredness".Pratt and Chiang’s version and Sanders’version used a large number of notes carrying a sinological mission,revealing their respect for the original and their decision to inform and inspire their readers.We argue that cultural translation,whether aided by annotation or not,is predominantly an art about"glocalism"and that both author-centeredness and reader-centeredness can be reconciled,since ultimately they serve the same"communicative"purpose.

Topic-aware pivot language approach for statistical machine translation

The pivot language approach for statistical machine translation(SMT) is a good method to break the resource bottleneck for certain language pairs. However, in the implementation of conventional approaches, pivotside context information is far from fully utilized, resulting in erroneous estimations of translation probabilities. In this study, we propose two topic-aware pivot language approaches to use different levels of pivot-side context. The first method takes advantage of document-level context by assuming that the bridged phrase pairs should be similar in the document-level topic distributions. The second method focuses on the effect of local context. Central to this approach are that the phrase sense can be reflected by local context in the form of probabilistic topics, and that bridged phrase pairs should be compatible in the latent sense distributions. Then, we build an interpolated model bringing the above methods together to further enhance the system performance. Experimental results on French-Spanish and French-German translations using English as the pivot language demonstrate the effectiveness of topic-based context in pivot-based SMT.

中国典籍英译研究现状与热点——基于国家级社科基金资助项目的统计分析(2005-2022)

国家社科基金和教育部人文社科基金是我国人文社会科学研究领域最权威的两大资助基金,受其资助的项目具有导向性、权威性和示范性作用,对这些项目进行统计分析有助于了解各学科当前的研究热点和状态,为相关的研究选题提供指导。基于翻译研究的分类视角,采用内容分析法,对近18年(2005-2022)的国家社科基金和教育部人文社科基金资助的典籍英译研究立项情况和主题内容进行统计和量化分析。研究发现:(1)语言学在典籍英译领域的学科优势依旧明显;(2)汉语典籍英译研究同少数民族典籍英译研究在课题数量上的差距依旧悬殊;(3)文学和哲学典籍英译研究仍是当前典籍英译研究的主流;(4)以文本外译、传播与接受为主题的研究成为典籍英译研究的热点;(5)数字人文技术在典籍英译研究领域的应用有待加强。

交互式机器翻译综述

随着深度学习的发展和成熟,神经机器翻译的质量也越来越高,然而仍不完美,为了达到可接受的翻译效果,需要人工进行后期编辑。交互式机器翻译(IMT)是这种串行工作的一个替代,即在翻译过程中进行人工互动,由用户对翻译系统产生的候选翻译进行验证,并且,如有必要,由用户提供新的输入,系统根据用户当前的反馈生成新的候选译文,如此往复,直到产生一个使用户满意的输出。首先,介绍了IMT的基本概念以及当前的研究进展;然后,分类对一些常用方法和前沿工作加以介绍,并简述每个工作的背景和创新之处;最后,探讨了IMT的发展趋势和研究难点。

异步共踵:清末民初统计学著作的译述与编写

中国近代意义上的统计学,是从西方移植来的。在晚清西学东渐浪潮的推动下,翻译来的统计学著作主要包括两类:一是从印欧语系直接翻译而来的各国统计年鉴;二是从日本转译而来的日本学者译著的统计学著作,日本学者将英语statistic音译为tokei,或译作政表、表记、制表或作综计,该词而后由日本辗转传入中国。日本统计学译本的翻译出版,标志着中国现代统计学的发轫。在译介西方统计学已有成果的基础上,中国学者开始探索编著各种统计学讲义,以适用于新式学堂的教学之用。早期的知识精英们对西方现代统计知识的认知与接受,并非是简单的他者渗入与移植,而是一场由西方文化传播者与本土接受者共同参与的复杂的在地化知识生产的过程。随着新式学堂的普遍建立、七科之学的逐渐形成,统计学在新学制中占有一席之地,亦随之在中国逐渐成长为一门独立的现代学科。

2009-2021年中国非物质文化遗产英译及外宣研究综述

以中国知网2009年至2021年关键词为“非物质文化遗产+翻译”与“非物质文化遗产+外宣”的论文为研究对象,通过统计其总量、核心期刊发文数量、覆盖区域、依托理论、英译难点、翻译策略、传播建议等,分析中国非物质文化遗产英译及外宣研究的特点及发展趋势。发现该领域研究尚存在受关注度不够、翻译人才短缺、地区发展不平衡、多模态传播模式研究缺乏、译法衡量标准不统一、研究语料未成体系、翻译批评手段传统等问题。建议强化政府、翻译机构、高校等非遗翻译传播意识,加强人才培养;打破地域限制,多开展同类别非遗英译及外宣研究;发布权威英译外宣标准,构建统一术语库;整理并创建多种类别的非遗语料库;开展描述性非遗英译策略研究,加强受众及接受效果研究。

儿童幻想小说中戏仿诗歌翻译的美学阐释——以《爱丽丝漫游奇境记》为例

《爱丽丝漫游奇境记》之经典不仅体现于奇幻冒险的故事,更体现于对经典诗歌戏仿所呈现出的文字游戏精神与气质,在翻译传播中,如果只局限在文本层面的对应,而忽视目标语读者的接受与喜爱,就会影响作品的传播。从接受美学视角出发,通过贝叶斯统计与问卷调查,并结合第三方语言德语译本研究发现:译者既是源语信息的读者又是二度创作者,可以根据翻译目的进行更为自由地发挥。在翻译过程中,译者需充分理解源文中的文字游戏精神和气质,同时根据目标语读者的接受与喜爱,以实现对源文的创造性翻译。如果脱离戏仿原型时代背景,把戏仿诗歌当作普通诗歌翻译,读者就无法产生共鸣,因而难以体会作品颠三倒四的荒诞之美。译者翻译中应考虑儿童读者的心理特殊性,以儿童读者理解接受为目标,实现风格的等效建构。

面向医药领域的深层语义解析

基于医药领域中文文本的解析难点,文章提出了一种面向中文医药领域的深层语义解析模型DSACM,该模型可将中文医药文本翻译为相应的意义,并将其视为一个机器翻译过程。具体而言,该模型通过统计词对齐模型获取双语词典,词典中包含自然语言字符串及其对应的MRL表示。文章用函数式查询语言(Med-FunQL)构造了可用于评测深层语义解析模型的性能的数据集(MEDQUARY),同时融入了美国国家地理数据库(GEOQUERY),为中文医药领域的研究提供了中文评测数据集。实验结果表明,文章提出的方法在数据集MEDQUERY中的实验结果准确率为80.4%,召回率为62.3%,F1值为70.8%;在中文版GEOQUERY中的实验结果准确率为71.9%,召回率为56.4%,F1值为62.1%,以上数据说明该统计机器翻译技术可被用于医药领域的中文语义解析。

2005统计机器翻译研讨班研究报告

2005年7月13日至15日,中国科学院自动化研究所、计算技术研究所和厦门大学计算机系联合举办了我国首届统计机器翻译研讨班。本文主要介绍本次研讨班参加单位的测试系统和实验结果,并给出相应的分析。测试结果表明,我国的统计机器翻译研究起步虽晚,但已有快速进展,参评系统在短期内得到了较好的翻译质量,与往年参加863评测的基于规则方法的系统相比性能虽还有差距,但差距已经不大。从目前国际统计机器翻译研究的现状和发展趋势来看,随着数据资源规模的不断扩大和计算机性能的迅速提高,统计机器翻译还有很大的发展空间。在未来几年内,在基于短语的主流统计翻译方法中融入句法、语义信息,必将成为机器翻译发展的趋势。