检索结果-南通市图书馆

Densely-connected neural networks for aspect term extraction

Science China(Information Sciences) 2022年第6期65卷 264-266页

作者： Chen CHEN Houfeng WANG Qingqing ZHU Junfei LIU School of Software and Microelectronics Peking University MOE Key Lab of computational linguistics School of Electronics Engineering and Computer SciencePeking University National Engineering Research Center for Software Engineering (Peking University)

Dear editor,Aspect term extraction(ATE) is a sub-task of aspect-based sentiment analysis, which aims to extract opinionated aspect terms from user reviews. For example, in a laptop domain review: “Boot time is super ... 详细信息

关键词： aspect term extraction recurrent neural network self-attention densely-connected network double word embeddings Aspect-Based Sentiment Analysis deep learning sequence labeling

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Acquiring Selectional Preferences in a Thai Lexical Database

Acquiring Selectional Preferences in a Thai Lexical Database

引用

第一届自然语言处理联合学术会议

作者： Canasai Kruengkrai Thatsanee Charoenporn Virach Sornlertlamvanich Hitoshi Isahara Thai computational linguistics laboratory Communications Research laboratory 112 Paholyothin Road Klong 1 Klong Luang Pathumthani 12120 Thai computational linguistics laboratory Communications Research laboratory 112 Paholyothin Road Klong 1 Klong Luang Pathumthani 12120 Thai computational linguistics laboratory Communications Research laboratory 112 Paholyothin Road Klong 1 Klong Luang Pathumthani 12120 Thai computational linguistics laboratory Communications Research laboratory 112 Paholyothin Road Klong 1 Klong Luang Pathumthani 12120

＜正＞In this paper, we consider the problem of enriching a Thai lexical database by extending the semantic information with seiectional preferences. We propose a novel approach for acquiring selectional preferences of verbs, which is motivated by the tree cut model. We apply a model selection technique called the Bayesian Information Criterion （BIC）. Given a semantic hierarchy, our goal is to generalize initial noun classes to the most plausible levels on that hierarchy. We present an iterative algorithm for generalization. The algorithm performs agglomerative merging on the semantic hierarchy in a bottomup manner. The BIC is used to measure the improvement of the model both locally and globally. In our experiments, we consider the Web as large corpora. We also propose approaches for extracting examples from the Web. Preliminarily experimental results are given to show the feasibility and effectiveness of our approach.

关键词：

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Translating Multi Word Terms into Korean from Chinese Documents

Translating Multi Word Terms into Korean from Chinese Docume...

引用

IEEE自然语言处理与知识工程国际学术会议

作者： Byeong-Kwu KANG The Institute of computational linguistics Peking University Beijing 100871 China

＜正＞This paper suggests a methodology which is aimed to translate the Chinese terms into Korean. Our basic idea is to use a method which combines domain-tuned dictionary and target language corpus. The translation system used in our work operated at three steps: （1） Tokenization of the term candidate;（2） Translation of term candidates using domain-tuned bilingual lexicon;（3） Ranking the translation candidate to recommend the best translation according to the frequency of the target word cooccurrence in the corpus. And we have demonstrated the effectiveness of our approach by showing a high degree of accuracy evaluation. Our experiments indicate a significant improvement when measured against un-tuned Chinese-Korean MT system.

关键词：

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Scaling Conditional Random Fields by One-Against-the-Other Decomposition

引用

Journal of Computer Science & Technology 2008年第4期23卷 612-619页

作者：赵海揭春雨 Department of Chinese Translation and LinguisticsCity University of Hong Kong83 Tat Chee Avenue Kowloon

As a powerful sequence labeling model, conditional random fields （CRFs） have had successful applications in many natural language processing （NLP） tasks. However, the high complexity of CRFs training only allows a very small tag （or label） set, because the training becomes intractable as the tag set enlarges. This paper proposes an improved decomposed training and joint decoding algorithm for CRF learning. Instead of training a single CRF model for all tags, it trains a binary sub-CRF independently for each tag. An optimal tag sequence is then produced by a joint decoding algorithm based on the probabilistic output of all sub-CRFs involved. To test its effectiveness, we apply this approach to tackling Chinese word segmentation （CWS） as a sequence labeling problem. Our evaluation shows that it can reduce the computational cost of this language processing task by 40-50% without any significant performance loss on various large-scale data sets.

关键词： natural language processing machine learning conditional random fields Chinese word segmentation

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Wavelet Neural Networks for Adaptive Equalization by Using the Orthogonal Least Square Algorithm

引用

Tsinghua Science and Technology 2004年第1期9卷 24-29,37页

作者：江铭虎邓北星 Georges Gielen Lab of computational linguistics Department of Chinese Language Tsinghua University Beijing 100084 China Department of Electronic Engineering Tsinghua University Beijing 100084 China Department of Electrical Engineering K.U.Leuven Kasteelpark Arenberg 10 B3001 Heverlee Belgium

Equalizers are widely used in digital communication systems for corrupted or time varying channels. To overcome performance decline for noisy and nonlinear channels, many kinds of neural network models have been used in nonlinear equalization. In this paper, we propose a new nonlinear channel equalization, which is structured by wavelet neural networks. The orthogonal least square algorithm is applied to update the weighting matrix of wavelet networks to form a more compact wavelet basis unit, thus obtaining good equalization performance. The experimental results show that performance of the proposed equalizer based on wavelet networks can significantly improve the neural modeling accuracy and outperform conventional neural network equalization in signal to noise ratio and channel non-linearity.

关键词： adaptive equalization wavelet neural networks (WNNs) orthogonal least square (OLS)

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

CAMK1 activated downstream-induced apoptosis of no-tumor hepatitis/cirrhotic tissues(HBV or HCV infection) is associated with de novo' pyrimidine base coupling amino acid metabolism through UDP-N-acetylglucosamine and glutamine

CAMK1 activated downstream-induced apoptosis of no-tumor hep...

引用

细胞—生命的基础——中国细胞生物学学会2013年全国学术大会·武汉

作者： Lin Wang Juxiang Huang Minghu Jiang Haizhen Diao Huilei Zhou Xiaohe Li Zhenfu Jiang Biomedical Center School of Electronic EngineeringBeijing University of Posts and Telecommunications Lab of computational linguistics School of Humanities and Social SciencesTsinghua University

Calcium/calmodulin-dependent protein kinase I(CAMKl) activated downstream metabolism-mediated apoptosis network was computed the biological processes and occurrence numbers of gene ontology (GO) in low expression no-tumor hepatitis/cirrhotic tissues(HBV or HCV infection) compared with high expression(fold change >2) human hepatocellular carcinoma(HCC) for finding new biomarkers

关键词： CAMK1 low expression no-tumor hepatitis/cirrhotic tissues(HBV or HCV infection) activated downstream metabolism-mediated apoptosis

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Carbohydrate coupling phospholipid metabolism in IGF2BP3 activated feedback-induced human hepatocellular carcinoma(HBV or HCV infection)(HCC) development through mannose and sterol biosynthesis

Carbohydrate coupling phospholipid metabolism in IGF2BP3 act...

引用

细胞—生命的基础——中国细胞生物学学会2013年全国学术大会·武汉

Insulin-like growth factor 2 mRNA binding protein 3(IGF2BP3) activated up- and down-stream metabolism-mediated tumor development network was computed the biological processes and occurrence numbers of gene ontology(GO) in high expression(fold change≥2) human hepatocellular carcinoma(HCC) compared with low expression no-tumor hepatitis/cirrhotic tissues(HBV or HCV

关键词： IGF2BP3 high expression HCC activated up- and down-stream metabolism-mediated tumor development

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Macrophage differentiation coupling neutrophil chemotaxis in IGF2BP3 activated feedback-induced human hepatocellular carcinoma(HBV or HCV infection)(HCC) development through interleukin-8 and leukotriene biosynthesis

Macrophage differentiation coupling neutrophil chemotaxis in...

引用

细胞—生命的基础——中国细胞生物学学会2013年全国学...

Insulin-like growth factor 2 mRNA binding protein 3(IGF2BP3) activated up- and down-stream inflammatory immunity-mediated tumor development network was computed the biological processes and occurrence numbers of gene ontology(GO) in high expression(fold change≥2) human hepatocellular carcinoma(HCC) compared with low expression no-tumor hepatitis/cirrhotic tissues (HBV or HCV infection) for finding new biomarkers of diagnosis and therapy in hepatocellular

关键词： IGF2BP3 high expression HCC activated up- and down-stream inflammatory immunity-mediated tumor development

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Activated PTHLH coupling feedback microtubule cytoskeleton organization to nucleic acid metabolism-induced regulation of cell growth network in HCC by systems-computational analysis

Activated PTHLH coupling feedback microtubule cytoskeleton o...

引用

第五届全国生物信息学与系统生物学学术大会暨国际生物信息学前沿研讨会高通量时代的生物信息学与系统生物学

作者： Lin Wang Juxiang Huang Minghu Jiang Hong Lin Lianxiu Qi Haizhen Diao Biomedical Center School of Electronic EngineeringBeijing University of Posts and Telecommunications Lab of computational linguistics School of Humanities and Social SciencesTsinghua University

Background:Our aim is to study novel high expression activated PTHLH feedback network-mediated regulation of cell growth mechanism in HCC. Methods:We studied the different biological processes and occurrence numbers between high expression(fold change >2) activated PTHLH feedback network-mediated regulation of cell growth gene ontology(GO) network of human hepatocellular carcinoma(HCC) compared with the corresponding low expression activated GO network of no-tumor hepatitis/cirrhotic tissues(HBV or HCV infection).We constructed activated PTHLH coupling feedback microtubule cytoskeleton organization to nucleic acid metabolism-induced regulation of cell growth network from GEO data set using gene regulatory network inference method and our programming. Results:Activated PTHLH feedback network-mediated regulation of cell growth network consisted of DNA repair,microtubule cytoskeleton organization and biogenesis,nucleotide and nucleic acid metabolism,oxidation reduction,protein modification,proteolysis,regulation of cell growth in *** PTHLH coupling feedback microtubule cytoskeleton organization to nucleic acid metabolism-induced regulation of cell growth network included upstream MAPT,TK1,ESM1,and downstream ESM1,TUBG1,TK1 in HCC. Conclusions:We proposed activated PTHLH coupling feedback microtubule cytoskeleton organization to nucleic acid metabolism-induced regulation of cell growth *** hypothesis was verified by the same activated PTHLH feedback networkmediated regulation of cell growth GO network of HCC with the corresponding inhibited GO network of no-tumor hepatitis/cirrhotic tissues,or the different with the corresponding inhibited GO network of HCC.

关键词： computation HCC activated PTHLH coupling feedback microtubule cytoskeleton organization to nucleic acid metabolism network activated PTHLH feedback regulation of cell growth network

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

IGF2BP3 activated feedback coupling G-protein signaling in human hepatocellular carcinoma(HBV or HCV infection)(HCC) development through activation of phospholipase A2,MAPK and NF-kappaB

IGF2BP3 activated feedback coupling G-protein signaling in h...

引用

细胞—生命的基础——中国细胞生物学学会2013年全国学术大会·武汉

Insulin-like growth factor 2 mRNA binding protein 3(IGF2BP3) activated up- and down-stream signal-mediated tumor development network was computed the biological processes and occurrence numbers of gene ontology(GO) in... 详细信息

关键词： IGF2BP3 high expression HCC activated up- and down-stream signal-mediated tumor development

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：