Web information retrieval based on temporal semantics is widely applied in the retrieval scenarios of dynamic temporal information mining,collective memory and temporal question answering system.By fully utilizing the...Web information retrieval based on temporal semantics is widely applied in the retrieval scenarios of dynamic temporal information mining,collective memory and temporal question answering system.By fully utilizing the temporal information contained in the Web documents.展开更多
Purpose-Time modeling is a crucial feature in many application domains.However,temporal information often is not crisp,but is subjective and fuzzy.The purpose of this paper is to address the issue related to the model...Purpose-Time modeling is a crucial feature in many application domains.However,temporal information often is not crisp,but is subjective and fuzzy.The purpose of this paper is to address the issue related to the modeling and handling of imperfection inherent to both temporal relations and intervals.Design/methodology/approach-On the one hand,fuzzy extensions of Allen temporal relations are investigated and,on the other hand,extended temporal relations to define the positions of two fuzzy time intervals are introduced.Then,a database system,called Fuzzy Temporal Information Management and Exploitation(Fuzz-TIME),is developed for the purpose of processing fuzzy temporal queries.Findings-To evaluate the proposal,the authors have implemented a Fuzz-TIME system and created a fuzzy historical database for the querying purpose.Some demonstrative scenarios from history domain are proposed and discussed.Research limitations/implications-The authors have conducted some experiments on archaeological data to show the effectiveness of the Fuzz-TIME system.However,thorough experiments on large-scale databases are highly desirable to show the behavior of the tool with respect to the performance and time execution criteria.Practical implications-The tool developed(Fuzz-TIME)can have many practical applications where time information has to be dealt with.In particular,in several real-world applications like history,medicine,criminal and financial domains,where time is often perceived or expressed in an imprecise/fuzzy manner.Social implications-The social implications of this work can be expected,more particularly,in two domains:in the museum to manage,exploit and analysis the piece of information related to archives and historic data;and in the hospitals/medical organizations to deal with time information inherent to data about patients and diseases.Originality/value-This paper presents the design and characterization of a novel and intelligent database system to process and manage the imperfection inherent to both temporal relations and intervals.展开更多
时序分析是自然科学和人文社会科学研究的常用方法,在信息检索领域也被广泛使用。本文采用定性与定量相结合的研究方法回顾并分析了1991至2016年时序分析的相关方法在信息检索领域内的应用情况。本文在Web of Science,EBSCOhost和Pro Qu...时序分析是自然科学和人文社会科学研究的常用方法,在信息检索领域也被广泛使用。本文采用定性与定量相结合的研究方法回顾并分析了1991至2016年时序分析的相关方法在信息检索领域内的应用情况。本文在Web of Science,EBSCOhost和Pro Quest三个数据库中检索了1991至2016年信息检索领域内使用时序分析相关方法的期刊论文、会议论文和学位论文,共计2240篇。本文采用趋势分析和文本内容分析方法对所获得的文献进行梳理和研究。研究结果显示在信息检索领域中,自2004年起时序分析方法的应用呈现明显上升趋势。时序分析方法包括定性和定量两大类,被广泛应用于传统(如文献计量、图书馆学等)、新兴(如社交媒体、商业智能等)的信息检索相关领域,及交叉学科(如健康信息等)的研究中。信息可视化方法和技术经常采用时序分析的理论和方法,同时也频繁地被用于时序分析的研究中。本文的研究结果将有助于信息检索领域的学者们进一步了解时序分析方法及其应用,并在日后的研究中更好地使用和创新时序分析方法。展开更多
Web image retrieval is a challenging task. One central problem of web image retrieval is to rank a set of images according to how well they meet the user information need. The problem of learning to rank has inspired ...Web image retrieval is a challenging task. One central problem of web image retrieval is to rank a set of images according to how well they meet the user information need. The problem of learning to rank has inspired numerous approaches to resolve it in the text information retrieval, related work for web image retrieval, however, are still limited. We focus on the problem of learning to rank images for web image retrieval, and propose a novel ranking model, which employs a genetic programming architecture to automatically generate an effective ranking function, by combining various types of evidences in web image retrieval, including text information, image visual content features, link structure analysis and temporal information. The experimental results show that the proposed algorithms are capable of learning effective ranking functions for web image retrieval. Significant improvement in relevancy obtained, in comparison to some other well-known ranking techniques, in terms of MAP, NDCG@n and D@n.展开更多
Temporal relation classification is one of contemporary demanding tasks of natural language processing. This task can be used in various applications such as question answering, summarization, and language specific in...Temporal relation classification is one of contemporary demanding tasks of natural language processing. This task can be used in various applications such as question answering, summarization, and language specific information retrieval. In this paper, we propose an improved algorithm for classifying temporal relations, between events or between events and time, using support vector machines （SVM）. Along with gold-standard corpus features, the proposed method aims at exploiting some useful automatically generated syntactic features to improve the accuracy of classification. Accordingly, a number of novel kernel functions are introduced and evaluated. Our evaluations clearly demonstrate that adding syntactic features results in a considerable improvement over the state-of-the-art method of classifying temporal relations.展开更多
文摘Web information retrieval based on temporal semantics is widely applied in the retrieval scenarios of dynamic temporal information mining,collective memory and temporal question answering system.By fully utilizing the temporal information contained in the Web documents.
文摘Purpose-Time modeling is a crucial feature in many application domains.However,temporal information often is not crisp,but is subjective and fuzzy.The purpose of this paper is to address the issue related to the modeling and handling of imperfection inherent to both temporal relations and intervals.Design/methodology/approach-On the one hand,fuzzy extensions of Allen temporal relations are investigated and,on the other hand,extended temporal relations to define the positions of two fuzzy time intervals are introduced.Then,a database system,called Fuzzy Temporal Information Management and Exploitation(Fuzz-TIME),is developed for the purpose of processing fuzzy temporal queries.Findings-To evaluate the proposal,the authors have implemented a Fuzz-TIME system and created a fuzzy historical database for the querying purpose.Some demonstrative scenarios from history domain are proposed and discussed.Research limitations/implications-The authors have conducted some experiments on archaeological data to show the effectiveness of the Fuzz-TIME system.However,thorough experiments on large-scale databases are highly desirable to show the behavior of the tool with respect to the performance and time execution criteria.Practical implications-The tool developed(Fuzz-TIME)can have many practical applications where time information has to be dealt with.In particular,in several real-world applications like history,medicine,criminal and financial domains,where time is often perceived or expressed in an imprecise/fuzzy manner.Social implications-The social implications of this work can be expected,more particularly,in two domains:in the museum to manage,exploit and analysis the piece of information related to archives and historic data;and in the hospitals/medical organizations to deal with time information inherent to data about patients and diseases.Originality/value-This paper presents the design and characterization of a novel and intelligent database system to process and manage the imperfection inherent to both temporal relations and intervals.
文摘时序分析是自然科学和人文社会科学研究的常用方法,在信息检索领域也被广泛使用。本文采用定性与定量相结合的研究方法回顾并分析了1991至2016年时序分析的相关方法在信息检索领域内的应用情况。本文在Web of Science,EBSCOhost和Pro Quest三个数据库中检索了1991至2016年信息检索领域内使用时序分析相关方法的期刊论文、会议论文和学位论文,共计2240篇。本文采用趋势分析和文本内容分析方法对所获得的文献进行梳理和研究。研究结果显示在信息检索领域中,自2004年起时序分析方法的应用呈现明显上升趋势。时序分析方法包括定性和定量两大类,被广泛应用于传统(如文献计量、图书馆学等)、新兴(如社交媒体、商业智能等)的信息检索相关领域,及交叉学科(如健康信息等)的研究中。信息可视化方法和技术经常采用时序分析的理论和方法,同时也频繁地被用于时序分析的研究中。本文的研究结果将有助于信息检索领域的学者们进一步了解时序分析方法及其应用,并在日后的研究中更好地使用和创新时序分析方法。
基金supported by the Natural Science Foundation of China (60970047)the Natural Science Foundation of Shandong Province (Y2008G19)the Key Science-Technology Project of Shandong Province (2007GG10001002, 2008GG10001026)
文摘Web image retrieval is a challenging task. One central problem of web image retrieval is to rank a set of images according to how well they meet the user information need. The problem of learning to rank has inspired numerous approaches to resolve it in the text information retrieval, related work for web image retrieval, however, are still limited. We focus on the problem of learning to rank images for web image retrieval, and propose a novel ranking model, which employs a genetic programming architecture to automatically generate an effective ranking function, by combining various types of evidences in web image retrieval, including text information, image visual content features, link structure analysis and temporal information. The experimental results show that the proposed algorithms are capable of learning effective ranking functions for web image retrieval. Significant improvement in relevancy obtained, in comparison to some other well-known ranking techniques, in terms of MAP, NDCG@n and D@n.
文摘Temporal relation classification is one of contemporary demanding tasks of natural language processing. This task can be used in various applications such as question answering, summarization, and language specific information retrieval. In this paper, we propose an improved algorithm for classifying temporal relations, between events or between events and time, using support vector machines （SVM）. Along with gold-standard corpus features, the proposed method aims at exploiting some useful automatically generated syntactic features to improve the accuracy of classification. Accordingly, a number of novel kernel functions are introduced and evaluated. Our evaluations clearly demonstrate that adding syntactic features results in a considerable improvement over the state-of-the-art method of classifying temporal relations.
