检索结果-内蒙古大学图书馆

H-tree: A hybrid structure for confidence computation in probabilistic databases

14th Asia Pacific Web Technology Conference, APWeb 2012

作者： Zhang, Qian Qin, Biao Wang, Shan Key Laboratory of Data Engineering and Knowledge Engineering Renmin University of China Ministry of Education Beijing 100872 China School of Information Renmin University of China Beijing 100872 China

ISBN: (纸本)9783642292521

Probabilistic database has become a popular tool for uncertain data management. Most work in the area is focused on efficient query processing and has two main directions, accurate or approximate evaluation. In recent work for conjunctive query without self-joins on a tuple-independent probabilistic database, query evaluation is equivalent to computing marginal probabilities of boolean formulas associated with query results. If formulas can be factorized into a read-once form where every variable appears at most once, confidence computation is reduced to a tractable problem that can be evaluated in linear time. Otherwise, it is regarded as a NP-hard problem and need to be evaluated approximately. In this paper, we propose a framework that evaluates both tractable and NP-hard conjunctive queries efficiently. First, we develop a novel structure H-tree, where boolean formulas are decomposed to small partitions which are either read-once or NP-hard. Then we propose algorithms for building H-tree and parallelizing (approximate) confidence computation. We also propose fundamental theorems to ensure the correctness of our approaches. Performance experiments demonstrate the benefits of H-tree, especially for approximate confidence evaluation on NP-hard queries. © 2012 Springer-Verlag Berlin Heidelberg.

关键词： Query processing

来源：评论

学校读者我要写书评

暂无评论

Discovering Reliable Information Extraction Patterns with Pre-Trained Model for Text with Writing Style

Discovering Reliable Information Extraction Patterns with Pr...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Bu, Chenyang Liu, Jiacheng Liu, Jiaxuan Ji, Shengwei Yang, Hongbin School of Computer Science and Information Engineering Ministry of Education Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Anhui Hefei230027 China School of Artificial Intelligence and Big Data Hefei University China

ISBN: (纸本)9798350337020

Large-scale pre-trained models such as GPT and BERT have demonstrated remarkable performance in information extraction tasks. However, their black-box nature poses challenges for reliability and interpretability. In contrast, rule- based extraction methods have better interpretability, but typically require domain experts to manually establish rules, limiting their generalization ability. In industry, there is often a demand for reliable knowledge extraction to reduce the time spent on manual verification of each piece of knowledge. In this paper, we explore the idea of combining GPT and symbolic-based methods to automatically discover reliable extraction patterns in text with a particular writing style. This method leverages the characteristics of high information density and similar writing patterns in text with a specific writing style to generate verifiable and reliable patterns. We conduct experiments on two datasets with a specific writing style to demonstrate its effectiveness, validating the idea of combining large models for reliable information extraction pattern discovery in the tested datasets. © 2023 IEEE.

关键词： Information extraction Reliable pattern Writing style data

来源：评论

学校读者我要写书评

暂无评论

Inductive Relation Prediction with Logical Reasoning Using Contrastive Representations

Inductive Relation Prediction with Logical Reasoning Using C...

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Pan, Yudai Liu, Jun Zhang, Lingling Zhao, Tianzhe Lin, Qika Hu, Xin Wang, Qianying School of Computer Science and Technology Xi'an Jiaotong University China National Engineering Lab for Big Data Analytics China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering China Lenovo Research Beijing China

Relation prediction in knowledge graphs (KGs) aims at predicting missing relations in incomplete triples, whereas the dominant embedding paradigm has a restriction on handling unseen entities during testing. In the real-world scenario, the inductive setting is more common because entities in the training process are finite. Previous methods capture an inductive ability by implicit logic in KGs. However, it would be challenging to preciously acquire entity-independent relational semantics of compositional logic rules and to deal with the deficient supervision of logic caused by the scarcity of relational semantics. To this end, we propose a novel graph convolutional network (GCN)-based model LogCo with logical reasoning by contrastive representations. LogCo firstly extracts enclosing subgraphs and relational paths between two entities to supply the entity-independence. Then a contrastive strategy for relational path instances and the subgraph is proposed for the issue of deficient supervision. The contrastive representations are learned for a joint training regime. Finally, prediction results and logic rules for reasoning are attained. Comprehensive experiments on twelve inductive datasets show that LogCo achieves outstanding performance comparing with SOTA inductive baselines. © 2022 Association for Computational Linguistics.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A neural network based forecasting method for the unemployment rate prediction using the search engine query data

A neural network based forecasting method for the unemployme...

引用

2011 8th IEEE International Conference on e-Business engineering, ICEBE 2011

作者： Xu, Wei Zheng, Tingting Li, Ziang Key Laboratory of Data Engineering and Knowledge Engineering Renmin University of China Ministry of Education Beijing 100872 China School of Information Renmin University of China Beijing 100872 China

ISBN: (纸本)9780769545189

Unemployment rate prediction has become critically important, because it can help government to make decision and design policies. In recent years, forecast of unemployment rate attracts much attention from governments, organizations, and research institutes, and researchers. Recently, a novel method using search engine query data to forecast unemployment was proposed by scholars. In this paper, a data mining based framework using web information is introduced for unemployment rate prediction. Under the framework, a neural network method, as one of the most effective data mining tools, is developed to forecast unemployment trend using search engine query data. In the proposed method, search engine query data related with employment activities is firstly found. Secondly, feature selection models including correlation coefficient method and genetic algorithm are constructed to reduce the dimension of the query data. Thirdly, various neural networks are employed to model the relationship between unemployment rate data and query data. Fourthly, an optimal neural network is selected as the selective predictor by using the cross-validation method. Finally, the selective neural network predictor with the best feature subset is used to forecast unemployment trend. The empirical results show that the proposed method clearly outperforms the classical forecasting approaches for the unemployment rate prediction. These findings imply that data mining method, such as neural networks, together with web information, can be used as an alternative tool to forecast social/economic hotspot. © 2011 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Optimizing queries with expensive video predicates based on estimation of attribute cardinality

Optimizing queries with expensive video predicates based on ...

引用

International Conference on Multimedia Information Networking and Security

作者： Yu, Lisheng Zhang, Jianmei Wang, Shan Key Laboratory of Ministry of Education for Data Engineering and Knowledge Engineering Renmin University of China Beijing 100872 China School of Information Renmin University of China Beijing 100872 China

ISBN: (纸本)9780769542584

With rapid advances in video processing technologies, video data increased rapidly and becomes popular in our daily life for both professional and consumer applications, e.g., surveillance, education, entertainment. Such needs require the data management system not only can store and access the video content, but also able to optimize the queries with expensive video predications in an effective and efficient way. In previous research literature, query optimizations in relational database systems (RDBMS) are often based on disk I/O cost of involved operations. However, for a query that contains expensive video predicates, traditional cost estimation model does not work well. Although researchers have proposed some approaches which can solve the problem in certain situations, there are still some unresolved issues, and it needs further optimization. In this paper, motivate from a real-world large supermarket's business data and video surveillance data management scenario, through considering the characteristics of video data and its expensive processing, we propose a novel query optimization approach that caches operators' results and reconstructs the join order based estimation for attribute cardinality. This approach reduces the invoking times of expensive video predicate in a greater degree and gives a better solution for mixed query optimization which contains traditional data types and large object operations. The experiment result is satisfactory while compare with existing expensive predicates query optimization methods. © 2010 IEEE.

关键词： Relational database systems

来源：评论

学校读者我要写书评

暂无评论

Random rough subspace based neural network ensemble for insurance fraud detection

Random rough subspace based neural network ensemble for insu...

引用

International Workshop on Computational Transportation Science

作者： Xu, Wei Wang, Shengnan Zhang, Dailing Yang, Bo Key Laboratory of Data Engineering and Knowledge Engineering School of Information Renmin University of China Beijing 100872 China School of Information Renmin University of China Beijing 100872 China

ISBN: (纸本)9780769543352

In this paper, a random rough subspace based neural network ensemble method is proposed for insurance fraud detection. In this method, rough set reduction is firstly employed to generate a set of reductions which can keep the consistency of data information. Secondly, the reductions are randomly selected to construct a subset of reductions. Thirdly, each of the selected reductions is used to train a neural network classifier based on the insurance data. Finally, the trained neural network classifiers are combined using ensemble strategies. For validation, a real automobile insurance case is used to test the effectiveness and efficiency of our proposed method with two popular evaluation criteria including the percentage correctly classified (PCC) and the receive operating characteristic (ROC) curve. The experimental results show that our proposed model outperforms single classifier and other models used in comparison. The findings of this study reseal that the random rough subspace based neural network ensemble method can provide a faster and more accurate way to find suspicious insurance claims, and it is a promising tool for insurance fraud detection. © 2011 IEEE.

关键词： Insurance

来源：评论

学校读者我要写书评

暂无评论

Short Text Topic Modeling Techniques, Applications, and Performance: A Survey

引用

IEEE Transactions on knowledge and data engineering 2022年第3期34卷 1427-1445页

作者： Qiang, Jipeng Qian, Zhenyu Li, Yun Yuan, Yunhao Wu, Xindong Department of Computer Science Yangzhou University Jiangsu225009 China Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology Hefei Anhui230026 China Mininglamp Academy of Sciences Minininglamp Beijing China

Analyzing short texts infers discriminative and coherent latent topics that is a critical and fundamental task since many real-world applications require semantic understanding of short texts. Traditional long text topic modeling algorithms (e.g., PLSA and LDA) based on word co-occurrences cannot solve this problem very well since only very limited word co-occurrence information is available in short texts. Therefore, short text topic modeling has already attracted much attention from the machine learning research community in recent years, which aims at overcoming the problem of sparseness in short texts. In this survey, we conduct a comprehensive review of various short text topic modeling techniques proposed in the literature. We present three categories of methods based on Dirichlet multinomial mixture, global word co-occurrences, and self-aggregation, with example of representative approaches in each category and analysis of their performance on various tasks. We develop the first comprehensive open-source library, called STTM, for use in Java that integrates all surveyed algorithms within a unified interface, benchmark datasets, to facilitate the expansion of new methods in this research field. Finally, we evaluate these state-of-the-art methods on many real-world datasets and compare their performance against one another and versus long text topic modeling algorithm. © 2020 IEEE.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Random analysis of statistical rough set

Random analysis of statistical rough set

引用

2016 International Conference on Machine Learning and Cybernetics, ICMLC 2016

作者： Tsang, Eric C.C. Zhao, Su-Yun Faculty of Information Technology Macau University of Science and Technology C-Macau China Key Laboratory of Data Engineering and Knowledge Engineering MOE Renmin University of China Beijing China

ISBN: (纸本)9781509003891

Attribute reduction is an inevitable problem in machine learning and statistical learning. To improve the traditional rough set reduction, statistical rough sets is then proposed by introducing random sampling into the rough approximation. Random sampling is the main contribution of statistical rough sets. As a result, it is necessary to analyze the randomness of statistical rough sets. In this paper, we analyze and demonstrate the influence of the randomness in the process of attribute reduction by a large number of experiments to test the effectiveness and stability of the random sampling. © 2016 IEEE.

关键词： Sampling

来源：评论

学校读者我要写书评

暂无评论

Detecting spam comments with malicious users'behavioral characteristics

Detecting spam comments with malicious users'behavioral char...

引用

2010 IEEE International Conference on Information Theory and Information Security, ICITIS 2010

作者： Wang, Qianqian Liang, Bin Shi, Wenchang Liang, Zhaohui Sun, Wei Key Laboratory of Data Engineering and Knowledge Engineering School of Information Renmin University of China Beijing China Beijing Venustech Cybervision Co. Ltd Beijing 100094 China

ISBN: (纸本)9781424469406

In recent years, the spread of spam comments has become a main obstacle which limits the development of commercialized social networks. This paper analyzes the differences of behavioral characteristics between normal users and malicious users. Based on these characteristics, we propose several heuristic methods to detect spam comments. These methods evaluate comments from three perspectives, including time-frequency characteristic of comments, text similarity of comments and the number of target domains each user's comments refer to. In our collected dataset, our experimental results indicate the accuracy of our detection strategy I (strategy for high accuracy) and strategy II (strategy for wide coverage) are 100% and 92.6%, respectively. The preliminary evaluation of the proposed detection methods shows promising result. © 2010 IEEE.

关键词： Heuristic methods

来源：评论

学校读者我要写书评

暂无评论

Measuring semantic association in domain ontology

Measuring semantic association in domain ontology

引用

3rd International Conference on Semantics, knowledge, and Grid, SKG 2007

作者： Tian, Xuan Li, HaiHua Du, Xiaoyong School of Information Renmin University of China Beijing 100872 China School of Information Renmin University of China Key Laboratory of Data Engineering and Knowledge Engineering Beijing 100872 China

ISBN: (纸本)0769530079

In domain ontology, Semantic Association(SA) is used to depict the correlation between two concepts. In this paper, we define Semantic Association Degree(SAD) for measuring SA in the domain ontology. We first present a method to measure SAD of two direct related concepts by evaluating the semantic relationship between them, and then give another method to measure SAD of two indirect related concepts though SAD of two directed neighboring concepts. A set of comparison experiments show the benefit of our approaches. © 2007 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：