检索结果-南通市图书馆

Sentiment analysis using deep learning approaches:an overview

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2020年第1期63卷 21-56页

作者： Olivier HABIMANA Yuhua LI Ruixuan LI xiwu gu Ge YU School of Computer Science and Technology Huazhong University of Science and Technology School of Computer Science and Engineering Northeastern University

Nowadays, with the increasing number of Web 2.0 tools, users generate huge amounts of data in an enormous and dynamic way. In this regard, the sentiment analysis appeared to be an important tool that allows the automation of getting insight from the user-generated data. Recently, deep learning approaches have been proposed for different sentiment analysis tasks and have achieved state-of-the-art results. Therefore, in order to help researchers to depict quickly the current progress as well as current issues to be addressed, in this paper, we review deep learning approaches that have been applied to various sentiment analysis tasks and their trends of development. This study also provides the performance analysis of different deep learning models on a particular dataset at the end of each sentiment analysis task. Toward the end, the review highlights current issues and hypothesized solutions to be taken into account in future work. Moreover, based on knowledge learned from previous studies, the future work subsection shows the suggestions that can be incorporated into new deep learning models to yield better performance. Suggestions include the use of bidirectional encoder representations from transformers(BERT), sentiment-specific word embedding models, cognition-based attention models, common sense knowledge, reinforcement learning, and generative adversarial networks.

关键词： sentiment analysis opinion mining deep learning neural network natural language processing(NLP) social network

Cache Coherency Design in Pentium Ⅲ SMP System

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Wuhan University Journal of Natural Sciences 2006年第2期11卷 360-364页

作者： LIU Jinsong ZHANG Jiangling gu xiwu Key Laboratory of Data Storage System Huazhong University of Science and Technology Wuhan 430074 Hubei China

This paper analyzes cache coherency mechanism from the view of system. It firstly discusses caehe-memory hierarchy of Pentium Ⅲ SMP system, including memory area distribution, cache attributes control and bus transaction. Secondly it analyzes hardware snoopy mechanism of P6 bus and MESI state transitions adopted by Pentium Ⅲ. Based on these, it focuses on how muhiprocessors and the P6 bus cooperate to ensure cache coherency of the whole system, and gives the key of cache coherency design.

关键词： snoop cache coherency MESI protocol P6bus Pentium Ⅲ SMP system

Type-2 fuzzy description logic

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2011年第2期5卷 205-215页

作者： Ruixuan LI Kunmei WEN xiwu gu Yuhua LI Xiaolin SUN Bing LI Intelligent and Distributed Computing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan 430074 China State Key Laboratory of Software Engineering Wuhan University Wuhan 430072 China

Description logics （DLs） are widely employed in recent semantic web application systems. However, classical description logics are limited when dealing with imprecise concepts and roles, thus providing the motivation for this work. In this paper, we present a type-2 fuzzy attributive concept language with complements （ALC） and provide its knowledge representation and reasoning algorithms. We also propose type-2 fuzzy web ontology language （OWL） to build a fuzzy ontology based on type- 2 fuzzy ALC and analyze the soundness, completeness, and complexity of the reasoning algorithms. Compared to type-1 fuzzy ALC, type-2 fuzzy ALC can describe imprecise knowledge more meticulously by using the membership degree interval. We implement a semantic search engine based on type-2 fuzzy ALC and carry out experiments on real data to test its performance. The results show that the type-2 fuzzy ALC can improve the precision and increase the number of relevant hits for imprecise information searches.

关键词： description logic (DL) type-2 fuzzy attributive concept language with complements (ALC) fuzzy ontology reasoning semantic search engine

A Formal Model for BPEL4WS Description of Web Service Composition

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Wuhan University Journal of Natural Sciences 2006年第5期11卷 1311-1319页

作者： gu xiwu LU Zhengding College of Computer Science and Technology HuazhongUniversity of Science and Technology Wuhan 430074Hubei China

Communicating Sequential Processes （CSP） is a kind of process algebra, which is suitable for modeling and verifying Web service composition. This paper describes how to model Web service composition with CSP. A set of rules for translating composition constructor of Business Process Execution Language for Web Services （BPEL4WS） to CSP notations is defined. According to the rules that have been defined, the corresponding translation algorithm is designed and illustrated with examples . The methods for model checking, model verification and model simulation are also introduced.

关键词： communicating sequential processes Web service Web service composition business process execution language for Web services

基于多重关系异构网络的学术实体权威度评估方法研究

在线全文

学校读者我要写书评

暂无评论

情报学报 2014年第8期33卷 872-882页

作者：王平辜希武赵慧慧武汉大学信息管理学院武汉430072 华中科技大学计算机科学与技术学院武汉430074

面对海量的科技文献资源，如何评估文献、作者和研究机构的学术质量和可信度引起了广泛关注。在众多可信度评价标准中，权威度是优先和关键的评价指标。因此，对科技文献、作者和机构等学术实体的科技实力和权威度进行研究与量化评估具... 详细信息

面对海量的科技文献资源，如何评估文献、作者和研究机构的学术质量和可信度引起了广泛关注。在众多可信度评价标准中，权威度是优先和关键的评价指标。因此，对科技文献、作者和机构等学术实体的科技实力和权威度进行研究与量化评估具有很大的现实意义。本文利用文献、作者、机构等三类实体间的引用、合著、合作等关系建立异构网络模型，在此基础上提出了混合随机游走算法Co-AcademicRank定量计算文献、作者、机构的权威度，并基于MapReduce实现了分布式的Co-AcademicRank算法。最后通过对情报学和图书馆学数据集测试与分析，对比分析了PageRank和Co-ranking算法，验证了本模型的有效性、准确性和优越性。同时，实验比较了算法在单机环境下和Hadoop平台下的运行时间，证明了分布式算法的高效性和稳定性。

关键词：权威度学术实体异构网络评估 MapReduce

C2C电子商务交易的信用及风险评估方法研究

在线全文

学校读者我要写书评

暂无评论

通信学报 2009年第7期30卷 78-85页

作者：李瑞轩高昶辜希武卢正鼎华中科技大学计算机科学与技术学院智能与分布计算实验室湖北武汉430074

提出了一种改进的信用计分方法,该方法采用商品价格的区间分布来对成功交易进行加分,采用信用等级的扣分系数来对不同信用等级的失败交易进行扣分,可以解决信用炒作和周期欺骗问题。通过对信用风险的分析,在改进的信用计分模型的基础上... 详细信息

提出了一种改进的信用计分方法,该方法采用商品价格的区间分布来对成功交易进行加分,采用信用等级的扣分系数来对不同信用等级的失败交易进行扣分,可以解决信用炒作和周期欺骗问题。通过对信用风险的分析,在改进的信用计分模型的基础上,设计了一种网上交易的风险计算方法,该方法可以根据历史交易的情况以及当前交易的价格来对当前交易的风险进行评估。模拟实验结果表明,改进的信用计分方法具有较好的抗信用炒作和周期欺骗效果,所给出的风险评估方法对电子商务交易中的风险分析和预测是比较准确和有效的。

关键词：电子商务信用评价风险评估信任

Typed formal model for WS-CDL specification of web services composition

在线全文

学校读者我要写书评

暂无评论

Journal of Southeast University(English Edition) 2008年第3期24卷 300-307页

作者：辜希武李瑞轩卢正鼎华中科技大学计算机科学与技术学院武汉430074

In order to formally reason and verify web services composition described by web services choreography specification WS-CDL,a typed formal model named typed Abstract WS-CDL（web services choreography description language）for WS-CDL specifications is *** typed Abstract WS-CDL,the syntax of type and session,typing rules and operational semantics are formalized;the collaborations of web services are formally described by sessions;the operational semantics of a session can help to formally reason the execution of the choreography;the typing rules can help to formally check the data type consistency of exchanged information between web services and capture run-time errors due to type ***,the concepts of type assumption set extension and type assumption set compatibility are proposed,and the merging algorithm of type assumption sets is defined so as to eliminate type assumption *** on the formal model,typed mapping rules for mapping web services choreography to orchestration is also *** the typed mapping rules,orchestration stubs and their type assumption sets can be generated from a given choreography; thus, web services composition can be verified at choreography and orchestration levels,*** model is proved to have properties of type safety,and how the model can help to reason and verify web services composition is illustrated through a case study.

关键词： typed model web services composition web services choreography description language

在线全文

学校读者我要写书评

暂无评论

融合多源信息的知识表示学习

计算机科学与探索 2022年第3期16卷 591-597页

作者：夏光兵李瑞轩辜希武刘伟华中科技大学计算机科学与技术学院武汉430074

在知识图谱中,实体的文本描述信息、实体的层次类型信息和图的拓扑结构信息中隐藏着丰富的内容,它们可以形成对原始三元组的有效补充,帮助提高知识图谱各种任务的效果。为了充分利用这些多源异质信息,首先通过一维卷积神经网络嵌入文本... 详细信息

在知识图谱中,实体的文本描述信息、实体的层次类型信息和图的拓扑结构信息中隐藏着丰富的内容,它们可以形成对原始三元组的有效补充,帮助提高知识图谱各种任务的效果。为了充分利用这些多源异质信息,首先通过一维卷积神经网络嵌入文本描述信息,然后根据实体的层次类型信息构建投影矩阵,将三元组中的实体向量和实体的描述向量映射到特定的关系空间中来约束实体的语义信息,再基于图注意力机制融合图的拓扑结构信息,计算不同邻接点对实体的影响。在图注意力层中,计算了实体间的多跳关系来帮助改善数据稀疏的问题。最后,通过二维卷积神经网络来捕获不同维度间的全局信息,进一步提高模型的性能。链接预测实验结果表明,基于多源信息组合的知识表示学习模型(MCKRL)能够充分利用三元组以外的多源异质信息,因而相比于其他基线模型,该模型在链接预测任务上取得了更好的结果。

关键词：知识表示学习实体描述层次类型拓扑结构

在线全文

学校读者我要写书评

暂无评论

文档级无触发词事件抽取联合模型

计算机科学与探索 2021年第12期15卷 2327-2334页

作者：王雷李瑞轩李玉华辜希武杨琪华中科技大学计算机科学与技术学院武汉430074

当前广为研究的在单个句子范围内的事件抽取方法,难以扩展到从分布在一篇文章里的多个句子中抽取同一事件的完整论元。对此,提出了一种基于深度学习的文档级事件抽取联合模型。首先,利用基于多头自注意力机制的实体识别模块逐句识别文... 详细信息

当前广为研究的在单个句子范围内的事件抽取方法,难以扩展到从分布在一篇文章里的多个句子中抽取同一事件的完整论元。对此,提出了一种基于深度学习的文档级事件抽取联合模型。首先,利用基于多头自注意力机制的实体识别模块逐句识别文档中的实体并输出其类型。然后,通过定义不同论元角色对事件类型的重要度训练事件类型检测模块,实现在无触发词条件下定位事件表述中心句并判断事件类型。最后,事件论元抽取模块通过在实体语义向量中嵌入实体的类型信息和实体到事件中心句的距离信息,并输入Transformer网络与上下文交换信息,实现在文档范围内抽取全部事件论元。通过对上述三个子模块进行联合训练,进一步实现了端到端的事件抽取,避免了管道式方法的误差传递。在公开数据集上的实验结果表明:在单事件条件下,该模型取得了86.3%的F1值,优于当前最佳的文档级事件抽取方法,并且具有优秀的模型训练速度。

关键词：文档级事件抽取无触发词联合模型实体识别事件检测