检索结果-南通市图书馆

维普期刊数据库

Personal summarization from profile networks

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2017年第6期11卷 1085-1097页

作者： zhongqing wang Shoushan LI Guodong ZHOU Natural Language Processing Lab School of Computer Science and Technology Soochow University Suzhou 215006 China

Personal profile information on social media like *** and *** is at the core of many inter- esting applications, such as talent recommendation and con- textual advertising. However, personal profiles usually lack consistent organization confronted with the large amount of available information. Therefore, it is always a challenge for people to quickly find desired information from them. In this paper, we address the task of personal profile summarization by leveraging both textual information and social connection information in social networks from both unsupervised and supervised learning paradigms. Here, using social connec- tion information is motivated by the intuition that people with similar academic, business or social background （e.g., co- major, co-university, and co-corporation） tend to have similar experiences and should have similar summaries. For unsu- pervised learning, we propose a collective ranking approach, called SocialRank, to combine textual information in an in- dividual profile and social context information from relevant profiles in generating a personal profile summary. For super- vised learning, we propose a collective factor graph model, called CoFG, to summarize personal profiles with local tex- tual attribute functions and social connection factors. Exten- sive evaluation on a large dataset from *** demon- strates the usefulness of social connection information in per- sonal profile summarization and the effectiveness of our pro- posed unsupervised and supervised learning approaches.

关键词： natural language processing machine learning,social networks personal profile summarization

Diagonalized Chebyshev Rational Spectral Methods for Second-Order Elliptic Problems on Unbounded Domains

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Numerical Mathematics(Theory,Methods and Applications) 2019年第1期12卷 265-284页

作者： Yanmin Ren Xuhong Yu zhongqing wang School of Science University of Shanghai for Science and TechnologyShanghai200093P.R.China

Diagonalized Chebyshev rational spectral methods for solving second-order elliptic problems on the half/whole line are *** Sobolev bi-orthogonal rational basis functions are constructed which lead to the diagonalization of discrete ***,both the exact solutions and the approximate solutions can be represented as infinite and truncated Fourier-like Chebyshev rational *** results demonstrate the effectiveness of the suggested approaches.

关键词： Chebyshev rational spectral methods Sobolev bi-orthogonal functions second-order elliptic equations numerical results

EFFICIENT AND ACCURATE CHEBYSHEV DUAL-PETROV-G ALERKIN METHODS FOR ODD-ORDER DIFFERENTIAL EQUATIONS

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computational Mathematics 2021年第1期39卷 43-62页

作者： Xuhong Yu Lusha Jin zhongqing wang School of Science University of Shanghai for Science and TechnologyShanghai 200093China

Efficient and accurate Chebyshev dual-Petrov-Galerkin methods for solving first-order equation,third-order equation,third-order KdV equation and fifth-order Kawahara equa-tion are *** Sobolev bi-orthogonal basis functions are constructed which lead to the diagonalization of discrete ***,both the exact solutions and the approximate solutions are expanded as an infinite and truncated Fourier-like series,*** experiments illustrate the effectiveness of the suggested approaches.

关键词： Chebyshev dual-Petrov-Galerkin method Sobolev bi-orthogonal polynomials Odd-order differential equations Numerical results.

Legendre-Gauss Spectral Collocation Method for Second Order Nonlinear Delay Differential Equations

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Numerical Mathematics(Theory,Methods and Applications) 2014年第2期7卷 149-178页

作者： Lijun Yi zhongqing wang Department of Mathematics Shanghai Normal UniversityShanghai 200234China Division of Computational Science of E-institute of Shanghai Universities Shanghai 200234China

In this paper, we present and analyze a single interval Legendre-Gaussspectral collocation method for solving the second order nonlinear delay differentialequations with variable delays. We also propose a novel algorithm for the singleinterval scheme and apply it to the multiple interval scheme for more efficient implementation. Numerical examples are provided to illustrate the high accuracy ofthe proposed methods.

关键词： Legendre-Gauss spectral collocation method second order nonlinear delay differential equations error analysis

Document structure model for survey generation using neural network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2021年第4期15卷 73-82页

作者： Huiyan XU zhongqing wang Yifei ZHANG Xiaolan WENG Zhijianwang Guodong ZHOU College of Computer and Information Hohai UniversityNanjing 210098China School of Computer Science and Technology Huaiyin Normal UniversityHuai’an 223300China Natural Language Processing Lab Soochow UniversitySuzhou 215006China

Survey generation aims to generate a summary from a scientific topic based on related *** structure of papers deeply influences the generative process of survey,especially the relationships between sentence and sentence,paragraph and *** principle,the structure of paper can influence the quality of the ***,we employ the structure of paper to leverage contextual information among sentences in paragraphs to generate a survey for *** particular,we present a neural document structure model for survey *** take paragraphs as units,and model sentences in paragraphs,we then employ a hierarchical model to learn structure among sentences,which can be used to select important and informative sentences to generate *** evaluate our model on scientific document data *** experimental results show that our model is effective,and the generated survey is informative and readable.

关键词： survey generation contextual information document structure

维普期刊数据库

Jacobi-Sobolev Orthogonal Polynomialsand Spectral Methods for Elliptic Boundary Value Problems

在线全文

学校读者我要写书评

暂无评论

Communications on Applied Mathematics and Computation 2019年第2期1卷 283-308页

作者： Xuhong Yu zhongqing wang Huiyuan Li University of Shanghai for Science and Technology Shanghai 200093China State Key Laboratory of Computer Science/Laboratory of Parallel Computing Institute of SoftwareChinese Academy of SciencesBeijing 100190China

Generalized Jacobi polynomials with indexes α,β∈ R are introduced and some basic properties are established. As examples of applications,the second- and fourth-order elliptic boundary value problems with Dirichlet or Robin boundary conditions are considered,and the generalized Jacobi spectral schemes are proposed. For the diagonalization of discrete systems,the Jacobi-Sobolev orthogonal basis functions are constructed,which allow the exact solutions and the approximate solutions to be represented in the forms of infinite and truncated Jacobi series. Error estimates are obtained and numerical results are provided to illustrate the effectiveness and the spectral accuracy.

关键词： Generalized Jacobi polynomials Spectral method - Jacobi-Sobolev orthogonal basis functions Elliptic boundary value problems Error analysis

Stance detection via sentiment information and neural network model

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2019年第1期13卷 127-138页

作者： Qingying SUN zhongqing wang Shoushan LI Qiaoming ZHU Guodong ZHOU Natural Language Processing Lab Soochow UniversitySuzhou 215006China Huaiyin Normal University Huai'an 223300China

Stance detection aims to automatically determine whether the author is in favor of or against a given *** principle,the sentiment information of a post highly influences the *** this study,we aim to leverage the sentiment information of a post to improve the performance of stance ***,conventional discrete models with sentimental features can cause error *** thus propose a joint neural network model to predict the stance and sentiment of a post simultaneously,because the neural network model can learn both representation and interaction between the stance and sentiment ***, we first learn a deep shared representation between stance and sentiment information,and then use a neural stacking model to leverage sentimental information for the stance detection *** studies demonstrate the effectiveness of our proposed joint neural model.

关键词： natural language processing machine learning stance detectionStance detection

Sentiment classification via user and product interactive modeling

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2021年第12期64卷 104-116页

作者： Xiabing ZHOU zhongqing wang Min ZHOU Qifa wang Shoushan LI Min ZHANG Guodong ZHOU School of Computer Science and Technology Soochow University

Sentiment classification aims to identify the polarity of a given review. Most existing methods consider each review as an individual while ignoring the importance of the user and product information of the given review. A direct way to integrate user and product information is to employ an attention mechanism to learn the local interaction between them. However, local interactions cannot capture the global optimization among user and product information. Therefore, we propose a novel interactive model to integrate both local and global interactions between users and products. In particular, we employ an attention mechanism to learn local interactions between users and products, and construct user and product interactive graphs to model the global interaction of users and products. Empirical evaluation shows that our model outperforms previous state-of-the-art methods significantly by learning the local and global interactions among users' preferences, product characteristics, and reviews.

关键词： product review analysis sentiment classification interactive graph graph convolutional network

同方期刊数据库

Preparation and performance of titanate nanotube by hydrothermal treatment

在线全文

学校读者我要写书评

暂无评论

Rare Metals 2008年第2期27卷 187-191页

作者： LI Zhenhua LIU zhongqing YAN Qingzhi wang Yichao GE Changchun Laboratory of Special Ceramics and Powder Metallurgy University of Science and Technology Beijing Beijing 100083 China

Titanate nanotubes were synthesized by hydrothermal treatment in concentrated NaOH solution followed by HCl washing. The as-prepared nanotubes were characterized by X-ray diffraction （XRD）, transmission electron microscopy （TEM）, and N2 adsorption-desorption isotherm measurements （BET）. The results displayed that the hydrothermal treatment temperature within 110-160℃ not only affected the structure of the nanotube, but also the anatase-to-rutile transformation temperature. The nanotube could be obtained only in an appropriate concentration of NaOH solution. The diameter of the nanotube was 6-10 nm. The surface area of the product initially increased with increasing treatment temperature, to reach a maximum of about 630 m^2/g at 130℃, and then decreased with a further increase in temperature.

关键词： nanotube titanate hydrothermal structure morphology

维普期刊数据库