In the information era,computer translation has attracted more and more translators' interests.MT(Machine Translation)and CAT(Computer Aided Translation)are closely connected with difference in essence.MT is conve...In the information era,computer translation has attracted more and more translators' interests.MT(Machine Translation)and CAT(Computer Aided Translation)are closely connected with difference in essence.MT is convenient but with many defects,while CAT has a great advantage with translation memory core technology.The features of CAT will make it the inevitable trend of future translation.展开更多
This paper describes the design of CEMT-Ⅱ, an interactive Chinese-English machine translation system. Based on the CEMT-Ⅰsystem, CEMT-Ⅱwill be developed to have the ability to translate Chinese scientific documents...This paper describes the design of CEMT-Ⅱ, an interactive Chinese-English machine translation system. Based on the CEMT-Ⅰsystem, CEMT-Ⅱwill be developed to have the ability to translate Chinese scientific documents into English. Now an user-friendly interface has been worked out to solve various complex ambiguities. The Chinese user need not know English well since all the questions and choices are expressed in Chinese.展开更多
Driven by the challenge of integrating large amount of experimental data, classification technique emerges as one of the major and popular tools in computational biology and bioinformatics research. Machine learning m...Driven by the challenge of integrating large amount of experimental data, classification technique emerges as one of the major and popular tools in computational biology and bioinformatics research. Machine learning methods, especially kernel methods with Support Vector Machines （SVMs） are very popular and effective tools. In the perspective of kernel matrix, a technique namely Eigen- matrix translation has been introduced for protein data classification. The Eigen-matrix translation strategy has a lot of nice properties which deserve more exploration. This paper investigates the major role of Eigen-matrix translation in classification. The authors propose that its importance lies in the dimension reduction of predictor attributes within the data set. This is very important when the dimension of features is huge. The authors show by numerical experiments on real biological data sets that the proposed framework is crucial and effective in improving classification accuracy. This can therefore serve as a novel perspective for future research in dimension reduction problems.展开更多
在汉越低资源翻译任务中,句子中的实体词准确翻译是一大难点。针对实体词在训练语料中出现的频率较低,模型无法构建双语实体词之间的映射关系等问题,构建一种融入实体翻译的汉越神经机器翻译模型。首先,通过汉越实体双语词典预先获取源...在汉越低资源翻译任务中,句子中的实体词准确翻译是一大难点。针对实体词在训练语料中出现的频率较低,模型无法构建双语实体词之间的映射关系等问题,构建一种融入实体翻译的汉越神经机器翻译模型。首先,通过汉越实体双语词典预先获取源句中实体词的翻译结果;其次,将结果拼接在源句末端作为模型的输入,同时在编码端引入“约束提示信息”增强表征;最后,在解码端融入指针网络机制,以确保模型能复制输出源端句的词汇。实验结果表明,该模型相较于跨语言模型XLM-R(Cross-lingual Language Model-RoBERTa)的双语评估替补(BLEU)值在汉越方向提升了1.37,越汉方向提升了0.21,时间性能上相较于Transformer该模型在汉越方向和越汉方向分别缩短3.19%和3.50%,可有效地提升句子中实体词翻译的综合性能。展开更多
文本生成图像(Text-to-Image,TTI)任务是指利用文本符号来生成图像,在艺术设计领域中有重要应用前景。由于缺乏不同语种的注释图像数据,对TTI的研究主要集中在英文领域,现有TTI模型无法利用其他语种数据进行图像生成。基于上述考虑,研...文本生成图像(Text-to-Image,TTI)任务是指利用文本符号来生成图像,在艺术设计领域中有重要应用前景。由于缺乏不同语种的注释图像数据,对TTI的研究主要集中在英文领域,现有TTI模型无法利用其他语种数据进行图像生成。基于上述考虑,研究多语种TTI(Multilingual TTI,MTTI)以及基于神经机器翻译引导的MTTI系统,依托多语种多模态编码器,提出基于多语种文本符号的艺术图像生成模型(Art Image Generation Model Based on Multilingual Text Symbols,AIG-MTS),学习权重并整合多语种文本知识,减少语种之间的差异,提高模型性能。在标准数据集COCO-CN、Multi30K Task2和LAION-5B上进行实验,相比于主流算法,AIG-MTS模型在所有数据集上的性能最佳。展开更多
基金supported in part by National Social Science Fund Project:CHA140176Education Scientific Planning Project of Anhui Province:JG10339
文摘In the information era,computer translation has attracted more and more translators' interests.MT(Machine Translation)and CAT(Computer Aided Translation)are closely connected with difference in essence.MT is convenient but with many defects,while CAT has a great advantage with translation memory core technology.The features of CAT will make it the inevitable trend of future translation.
文摘This paper describes the design of CEMT-Ⅱ, an interactive Chinese-English machine translation system. Based on the CEMT-Ⅰsystem, CEMT-Ⅱwill be developed to have the ability to translate Chinese scientific documents into English. Now an user-friendly interface has been worked out to solve various complex ambiguities. The Chinese user need not know English well since all the questions and choices are expressed in Chinese.
基金supported by Research Grants Council of Hong Kong under Grant No.17301214HKU CERG Grants,Fundamental Research Funds for the Central Universities+2 种基金the Research Funds of Renmin University of ChinaHung Hing Ying Physical Research Grantthe Natural Science Foundation of China under Grant No.11271144
文摘Driven by the challenge of integrating large amount of experimental data, classification technique emerges as one of the major and popular tools in computational biology and bioinformatics research. Machine learning methods, especially kernel methods with Support Vector Machines （SVMs） are very popular and effective tools. In the perspective of kernel matrix, a technique namely Eigen- matrix translation has been introduced for protein data classification. The Eigen-matrix translation strategy has a lot of nice properties which deserve more exploration. This paper investigates the major role of Eigen-matrix translation in classification. The authors propose that its importance lies in the dimension reduction of predictor attributes within the data set. This is very important when the dimension of features is huge. The authors show by numerical experiments on real biological data sets that the proposed framework is crucial and effective in improving classification accuracy. This can therefore serve as a novel perspective for future research in dimension reduction problems.
文摘在汉越低资源翻译任务中,句子中的实体词准确翻译是一大难点。针对实体词在训练语料中出现的频率较低,模型无法构建双语实体词之间的映射关系等问题,构建一种融入实体翻译的汉越神经机器翻译模型。首先,通过汉越实体双语词典预先获取源句中实体词的翻译结果;其次,将结果拼接在源句末端作为模型的输入,同时在编码端引入“约束提示信息”增强表征;最后,在解码端融入指针网络机制,以确保模型能复制输出源端句的词汇。实验结果表明,该模型相较于跨语言模型XLM-R(Cross-lingual Language Model-RoBERTa)的双语评估替补(BLEU)值在汉越方向提升了1.37,越汉方向提升了0.21,时间性能上相较于Transformer该模型在汉越方向和越汉方向分别缩短3.19%和3.50%,可有效地提升句子中实体词翻译的综合性能。
文摘文本生成图像(Text-to-Image,TTI)任务是指利用文本符号来生成图像,在艺术设计领域中有重要应用前景。由于缺乏不同语种的注释图像数据,对TTI的研究主要集中在英文领域,现有TTI模型无法利用其他语种数据进行图像生成。基于上述考虑,研究多语种TTI(Multilingual TTI,MTTI)以及基于神经机器翻译引导的MTTI系统,依托多语种多模态编码器,提出基于多语种文本符号的艺术图像生成模型(Art Image Generation Model Based on Multilingual Text Symbols,AIG-MTS),学习权重并整合多语种文本知识,减少语种之间的差异,提高模型性能。在标准数据集COCO-CN、Multi30K Task2和LAION-5B上进行实验,相比于主流算法,AIG-MTS模型在所有数据集上的性能最佳。
