检索结果-内蒙古大学图书馆

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Tang, Xiaobin Zhang, Jing Chen, Bo Yang, Yang Chen, Hong Li, Cuiping Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education Renmin University of China China Information School Renmin University of China China Zhejiang University China

ISBN: (纸本)9780999241165

knowledge graph alignment aims to link equivalent entities across different knowledge graphs. To utilize both the graph structures and the side information such as name, description and attributes, most of the works propagate the side information especially names through linked entities by graph neural networks. However, due to the heterogeneity of different knowledge graphs, the alignment accuracy will be suffered from aggregating different neighbors. This work presents an interaction model to only leverage the side information. Instead of aggregating neighbors, we compute the interactions between neighbors which can capture fine-grained matches of neighbors. Similarly, the interactions of attributes are also modeled. Experimental results show that our model significantly outperforms the best state-of-the-art methods by 1.9-9.7% in terms of HitRatio@1 on the dataset DBP15K. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Graph-Based Exercise- and knowledge-Aware Learning Network for Student Performance Prediction 1st

Graph-Based Exercise- and Knowledge-Aware Learning Network ...

引用

1st CAAI International Conference on Artificial Intelligence, CICAI 2021

作者： Liu, Mengfan Shao, Pengyang Zhang, Kun Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China

ISBN: (纸本)9783030930455

Predicting student performance is a fundamental task in Intelligent Tutoring Systems (ITSs), by which we can learn about students’ knowledge level and provide personalized teaching strategies for them. Researchers have made plenty of efforts on this task. They either leverage educational psychology methods to predict students’ scores according to the learned knowledge proficiency, or make full use of Collaborative Filtering (CF) models to represent latent factors of students and exercises. However, most of these methods either neglect the exercise-specific characteristics (e.g., exercise materials), or cannot fully explore the high-order interactions between students, exercises, as well as knowledge concepts. To this end, we propose a Graph-based Exercise- and knowledge-Aware Learning Network for accurate student score prediction. Specifically, we learn students’ mastery of exercises and knowledge concepts respectively to model the two-fold effects of exercises and knowledge concepts. Then, to model the high-order interactions, we apply graph convolution techniques in the prediction process. Extensive experiments on two real-world datasets prove the effectiveness of our proposed Graph-EKLN. © 2021, Springer Nature Switzerland AG.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

DB Facade: A web cache with improved data freshness

DB Facade: A web cache with improved data freshness

引用

2nd International Symposium on Electronic Commerce and Security, ISECS 2009

作者： Xiongpai, Qin Zhou, Xiaoyun Key Laboratory of Data Engineering and Knowledge Engineering School of Information Renmin University of China Beijing 100872 China School of Information and Electrical Engineering China University of Mining Technology Xuzhou Jiangsu 221008 China

ISBN: (纸本)9780769536439

Traditional web database cache techniques have a major disadvantage, namely poor data freshness, because they employ an asynchronous data refresh strategy. A novel web database cache, DB Façade, is proposed in this paper. DB Facade uses a main memory database to cache result sets of previous queries for subsequent reusing. Updates on backend database system are managed by delta tables, and then propagated to web database cache in a near real-time manner, hence guarantee the freshness of data. DB Facade offloads query burden from backend database systems, and exploits the power of main memory database system to boost query performance. TPC-W testing result shows that the system's performance increases by about 17 percent. © 2009 IEEE.

关键词： Facades

来源：评论

学校读者我要写书评

暂无评论

Multi-Label Truth Inference for Crowdsourcing Using Mixture Models

引用

IEEE Transactions on knowledge and data engineering 2021年第5期33卷 2083-2095页

作者： Zhang, Jing Wu, Xindong School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing 210094 China Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education Hefei 230009 China

When acquiring labels from crowdsourcing platforms, a task may be designed to include multiple labels and the values of each label may belong to a set of various distinct options, which is the so-called multi-class multi-label annotation. To improve the quality of labels, requesters usually let one task be independently completed by a group of heterogeneous crowdsourced workers. Then, the true values of the multiple labels of each task are inferred from these repeated noisy labels. In this paper, we propose two novel probabilistic models MCMLI and MCMLD to address the multi-class multi-label inference problem in crowdsourcing. MCMLI assumes that the labels of each task are mutually independent and MCMLD utilizes a mixture of multiple independently multinoulli distributions to capture the correlation among the labels. Both models can jointly infer multiple true labels of each instance as well as estimate the reliability of crowdsourced workers modeled by a set of confusion matrices with an expectation-maximization algorithm. Experiments with three typical crowdsourcing scenarios and a real-world dataset show that our proposed models significantly outperform existing competitive alternatives. When the labels are strongly correlated, MCMLD substantially outperforms MCMLI. Furthermore, our models can be easily simplified to the one-coin models, which show more advantageous when errors are uniformly distributed, or labels are sparse. © 1989-2012 IEEE.

关键词： Crowdsourcing maximum likelihood estimation mixture models probabilistic graphical models statistical inference

来源：评论

学校读者我要写书评

暂无评论

A method for measuring journal discriminative capacity and its application in WOS 15th

A method for measuring journal discriminative capacity and i...

引用

15th International Conference on Sustainable Digital Communities, iConference 2020

作者： Wang, Hao Zhang, Baolong Deng, Sanhong Su, Xinning School of Information Management Nanjing University Nanjing210023 China Jiangsu Key Laboratory of Data Engineering and Knowledge Service Nanjing210023 China

ISBN: (纸本)9783030436865

Journal discriminative capacity refers to the degree of difference between the journals in research subjects, and is of great significance for detecting the level of journal differentiation. Current research on journal discrepancies is predominantly focused on the quantitative analysis of journal content, and rarely measures the degree of journal difference. To address this lapse in research, a method from the perspective of difference is proposed in this paper to quantitatively measure and analyze the discriminative capacity of journals. Using the bibliographic of Science Citation Index (SCI), Social Science Citation Index (SSCI), and Arts & Humanities Citation Index (A&HCI) journals from 2015–2017 as the data source, the contents differences of 23 Library and Information Science (LIS) journals are analyzed through hierarchical clustering and journal discriminative capacity (JDC) measurement. The discriminative capacity of disciplines is then calculated and combined with multidimensional scaling analysis to detect the difference characteristics of journals in ten disciplines, and the mean JDC is used to explore the overall differences of disciplines. Results show that the discriminative capacity of LIS journals is obviously stratified, the journals of library science are the most discriminating, and the journals of evaluation and review are the weakest. In addition, the journals of different disciplines have distinct disciplinary characteristics, with the discriminative capacity of SCI journals as the most notable, followed by SSCI journals, and with A&HCI journals displaying the weakest discriminative capacity. © Springer Nature Switzerland AG 2020.

关键词： Digital libraries

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

A Semantic Framework for Chinese Historical Events Based on Linked data and knowledge Graph 16th

A Semantic Framework for Chinese Historical Events Based on ...

引用

16th International Conference on Diversity, Divergence, Dialogue, iConference 2021

作者： Wang, Hao Li, Yueyan Deng, Sanhong School of Information Management Nanjing University Nanjing210023 China Jiangsu Key Laboratory of Data Engineering and Knowledge Service Nanjing210023 China

ISBN: (纸本)9783030712914

In the era of big data, data redundancy has become an obstacle to deep reading. The objective of linked data as a new data organization model is to transform data into structured data following unified standards. The lack of Chinese conceptual terms has seriously hindered the semantization and standardization of Chinese domain ontology. Taking Chinese historical events as an example, ontology technology is used in this paper to standardize the definition of concepts and semantic relations in domain knowledge. Moreover, concepts from text resources are extracted through a deep learning algorithm Bi-LSTM-CRFs and combined with an external knowledge base to realize the fusion of related data within various data sets. Ultimately, the knowledge ontology of historical events is displayed in the way of a knowledge graph to further explore the practical application. The results show that the accuracy of the terms extraction of historical events is about 80% indicating the good recognition performance and portability of the model. © 2021, Springer Nature Switzerland AG.

关键词： Linked data

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

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

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：