Empirical study on character level neural network classifier for Chinese text
作者：
Chung, Tonglee;Xu, Bin;Liu, Yongbin* ;Ouyang, Chunping;Li, Siliang;...
期刊：
Engineering Applications of Artificial Intelligence ,2019年80:1-7 ISSN：0952-1976
通讯作者：
Liu, Yongbin
作者机构：
[Xu, Bin; Li, Siliang; Chung, Tonglee] Tsinghua Univ, Dept Comp Sci & Technol, Beijing 100084, Peoples R China.;[Ouyang, Chunping; Liu, Yongbin; Luo, Lingyun] Univ South China, Coll Comp Sci & Technol, Hengyang 421001, Peoples R China.
通讯机构：
[Liu, Yongbin] U;Univ South China, Coll Comp Sci & Technol, Hengyang 421001, Peoples R China.
关键词：
Character level classifier;CNN;Neural network;RNN
摘要：
Character level models are drawing attention recently. A number of these models have been proposed and shown successful in Natural Language Processing tasks. While most of the models are experimented mainly on English, or other alphabetic languages, a number of problems arise when they applied these models to non-alphabetic language such as Chinese. In this study, we investigated the problems encountered when transferring these models to the Chinese and put forward some solutions. We propose a double embedding neural network model that is also character level and consists of both CNN and RNN with two separate embeddings. The model is applied to a fundamental Natural Language Processing task, text classification. Experiment results conducted on the Chinese corpus demonstrated that our character level neural network model performs just as well as or better than those word level classification models. Our model is able to reach 95.9% accuracy on a Chinese Fudan news dataset, which outperforms the state-of-the-art models. © 2019
语种：
英文
展开
基于经营管理视角下企业新生代大学生激励因素研究
作者：
欧翠玲;刘洋;龙斯琪
期刊：
商场现代化 ,2017年(7):236-237 ISSN：1006-3102
作者机构：
南华大学经济管理学院;南华大学计算机科学与技术学院;[欧翠玲; 刘洋; 龙斯琪] 南华大学
关键词：
经营管理视角;新生代大学生;激励因素
摘要：
新生代大学生个性鲜明、大批步入职场，成为未来市场的主力军。互联网发展，市场国际化，人才竞争是企业可持续发展的关键。企业为有效经营管理组织，采取合理的激励因素吸引留住人才和获得组织-个人双赢是企业有效经营管理的重要研究课题。
语种：
中文
展开
云计算环境下电子商务退换货模式研究
作者：
欧翠玲;刘洋
期刊：
商场现代化 ,2017年(6):50-51 ISSN：1006-3102
作者机构：
南华大学经济管理学院;南华大学计算机科学与技术学院;[欧翠玲; 刘洋] 南华大学
关键词：
云计算;电子商务;退换货模式
摘要：
退换货是一种有效提高顾客满意度的售后服务方式.退换货服务涉及多方主体信息资源和利益关系,而云计算具有信息共享和大数据处理能力.文章分析了云计算环境下电子商务的退换货模式,为企业实施退换货模式提供了新的视角.
语种：
中文
展开
Ensemble method to joint inference for knowledge extraction
作者：
Liu, Yongbin;Ouyang, Chunping* ;Li, Juanzi
期刊：
Expert Systems with Applications ,2017年83:114-121 ISSN：0957-4174
通讯作者：
Ouyang, Chunping
作者机构：
[Ouyang, Chunping; Liu, Yongbin] Univ South China, Coll Comp Sci & Technol, Hengyang 421001, Peoples R China.;[Li, Juanzi; Liu, Yongbin] Tsinghua Univ, Dept Comp Sci & Technol, Beijing 100084, Peoples R China.
通讯机构：
[Ouyang, Chunping] U;Univ South China, Coll Comp Sci & Technol, Hengyang 421001, Peoples R China.
关键词：
Ensemble learning;Joint inference;Knowledge extraction;Markov logic network
摘要：
Joint inference is a fundamental issue in the field of artificial intelligence. The greatest advantage of the joint inference is demonstrated by its capability of avoiding errors from cascading and accumulating on a pipeline of multiple chained sub-tasks. Markov Logic Network(MLN) is the most common joint inference model that provides a flexible representation and handles uncertainty. It has been applied successfully to joint inference on many natural language processing tasks to avoid error propagation. However, due to the great expressiveness of first-order logic, the representation for it in MLN generates rather complicated graph structures, which makes the learning and inference on large scale data intractably. In this paper, we present an ensemble learning approach to deal with the challenges in MLNs. Firstly, we give a proof within the probably approximately correct (PAC) framework. The proof points out what conditions are necessary for successful applying the ensemble learning approach to MLN. Secondly, the paper explains how to combine the learners. Finally, in order to illustrate the working mechanism of the ensemble joint inference model, we present an Ensemble Markov Logic Networks (EMLNs) method and use it to extract knowledge from a large scale corpus published by Google.1 Experiments suggest that significant speedup can be gained by the EMLNs. Meanwhile, it show that this approach leads to a higher precision and recall than that of those pipeline approaches. © 2017 Elsevier Ltd
语种：
英文
展开
An estimate method of information influence based on citation analysis
作者：
Liu, Yang* ;Dong, Han;Xu, Lingyu;Yu, Jie;Xue, Yunlan
期刊：
The Journal of Information and Computational Science ,2015年12(1):121-131 ISSN：1548-7741
通讯作者：
Liu, Yang
作者机构：
[Yu, Jie; Xue, Yunlan; Liu, Yang; Xu, Lingyu] School of Computer Engineering and Science, Shanghai University, Shanghai, China;[Dong, Han] National Marine Data and Information Service, State Oceanic Administration, Tianjin, China;[Liu, Yang] School of Computer Science and Technology, University of South China, Hengyang, China
通讯机构：
School of Computer Engineering and Science, Shanghai University, Shanghai, China
关键词：
Forestry;Information dissemination;Academic paper;Citation analysis;Impacted domain;Influence power;Information domains;Knowledge tree;Multi-level structures;Reference values;Information analysis;Information Retrieval;Trees
摘要：
A method of information influence estimate is proposed in this paper which takes the citation analysis as instance. The estimate method based on knowledge tree which has a multilevel structure is built to research the rules of information dissemination and the relations between information influenced domains. Because the information influence has different reference value between information's own domain and the other domains, an estimate method of multiple perspectives is more useful than former methods which use one formula to estimate information influence. In the instance of citation analysis, academic paper is considered as information, and citation papers are influenced by the academic paper. Copyright © 2015 Binary Information Press.
语种：
英文
展开
Research on domain knowledge graph based on the large scale online knowledge fragment
作者：
Lv Qingjie* ;Xu Lingyu;Yu Jie;Wang Lei;Xun Yunlan;...
作者机构：
[Wang Lei; Xu Lingyu; Xun Yunlan; Lv Qingjie; Yu Jie] Shanghai Univ, Sch Comp Engn & Sci, Shanghai, Peoples R China.;[Shi Suixiang] State Ocean Adm, Natl Marine Data & Informat Serv, Tianjin, Peoples R China.;[Liu Yang] Univ South China, Sch Comp Sci & Technol, Hengyang, Peoples R China.
会议名称：
IEEE Workshop on Advanced Research and Technology in Industry Applications (WARTIA)
会议时间：
SEP 29-30, 2014
会议地点：
Ottawa, CANADA
会议主办单位：
[Lv Qingjie;Xu Lingyu;Yu Jie;Wang Lei;Xun Yunlan] Shanghai Univ, Sch Comp Engn & Sci, Shanghai, Peoples R China.^[Shi Suixiang] State Ocean Adm, Natl Marine Data & Informat Serv, Tianjin, Peoples R China.^[Liu Yang] Univ South China, Sch Comp Sci & Technol, Hengyang, Peoples R China.
关键词：
knowledge graph;multi-source;multidimensional;information fusion
摘要：
Knowledge Graph is a powerful tool to manage large scale knowledge, and is an important means to deal with the problem of the knowledge fragment. Knowledge Graph can be applied to Semantic Search, Question Answering System, Deep Reading and other. The current research mainly focuses on the information fusion of broad-spectrum knowledge, and aims at improving the recall ratio of the knowledge. Based on the previous research, we propose a method for constructing the domain knowledge Graph. We use information extraction technology to extract entities and relationships from open network documents. Meanwhile, we mine the multidimensional relationships between entities, and solve the information conflicts generated by multi-source information fusion. These are important to rich the information and improve the recall ratio and precision ratio of domain knowledge. So the method has important significance to build knowledge graph of specific areas.
语种：
英文
展开
Formal Concept Analysis Supporting Ontology Learning From Database
作者：
Chunping Ouyang;Yongbin Liu
期刊：
Advanced Science Letters ,2012年7(1):473-477 ISSN：1936-6612
通讯作者：
Ouyang, C.
作者机构：
[Ouyang C.] School of Computer Science and Technology, University of South China, Hengyang, 421001, China;[Liu Y.] Department of Information Science and Technology, Tianjin University of Finance and Economics, Tianjin, 300222, China
通讯机构：
[Ouyang, C.] S;School of Computer Science and Technology, , Hengyang, 421001, China
关键词：
Formal concept analysis;Ontology learning;Relational database
摘要：
Ontology learning is a process, which extracts semantic information from the existing data model and generates ontology using a set of predefined mapping rules. Relational database is the main model of data access and management, and extracting ontology from relational database is one of the research hotspots in ontology engineering field. This paper presents a proposal that aims to cover some tasks required in the ontology learning from relational database. Two tasks in this proposal are: relations abstraction between data table and semantics abstraction between data tuple. Formal Concept Analysis (FCA) is applied by the proposal to perform the listed tasks. The ontology learning from database based on FCA not only keeps the semantic information of relational data tables, but also shows the advantage of FCA in automatic extraction of semantics. Thus the quality of final ontology is improved and the application field of ontology is extended. © 2012 American Scientific Publishers. All Rights Reserved.
语种：
英文
展开
