基于词关联度的语义相关度算法研究

如今网页排名算法很多,基本上可以分为两类:基于超链接和基于内容。比较成熟的算法主要有PageRank、HITS、LSI等。本文基于向量空间模型以及信息论,提出一个与文章内容相关的语义相关度算法模型。该模型将文章语义抽象为词频表,并通过机器学习构建词语之间的关联度表,以此词关联度为基础,计算文章之间的相关度。实验结果表明,文中提出的相关度算法可以有效的根据文章之间语义相关度大小来进行排名。     

Evidence supporting measure of similarity for reducing the complexity in information fusion

This paper presents a new method for reducing the number of sources of evidence to combine in order to reduce the complexity of the fusion processing. Such a complexity reduction is often required in many applications where the real-time constraint and limited computing resources are of prime importance. The basic idea consists in selecting, among all sources available, only a subset of sources of evidence to combine. The selection is based on an evidence supporting measure of similarity (ESMS) criterion which is an efficient generic tool for outlier sources identification and rejection. The ESMS between two sources of evidence can be defined using several measures of distance following different lattice structures. In this paper, we propose such four measures of distance for ESMS and we present in details the principle of Generalized Fusion Machine (GFM). Then we apply it experimentally to the real-time perception of the environment with a mobile robot using sonar sensors. A comparative analysis of results is done and presented in the last part of this paper.     

Representing model theory in a type-theoretical logical framework

In a broad sense, logic is the field of formal languages for knowledge and truth that have a formal semantics. It tends to be difficult to give a narrower definition because very different kinds of logics exist. One of the most fundamental contrasts is between the different methods of assigning semantics. Here two classes can be distinguished: model theoretical semantics based on a foundation of mathematics such as set theory, and proof theoretical semantics based on an inference system possibly formulated within a type theory.Logical frameworks have been developed to cope with the variety of available logics unifying the underlying ontological notions and providing a meta-theory to reason abstractly about logics. While these have been very successful, they have so far focused on either model or proof theoretical semantics. We contribute to a unified framework by showing how the type/proof theoretical Edinburgh Logical Framework (LF) can be applied to the representation of model theoretical logics.We give a comprehensive formal representation of first-order logic, covering both its proof and its model theoretical semantics as well as its soundness in LF. For the model theory, we have to represent the mathematical foundation itself in LF, and we provide two solutions for that. Firstly, we give a meta-language that is strong enough to represent the model theory while being simple enough to be treated as a fragment of untyped set theory. Secondly, we represent Zermelo-Fraenkel set theory and show how it subsumes our meta-language. Specific models are represented as LF morphisms.All representations are given in and mechanically verified by the Twelf implementation of LF. Moreover, we use the Twelf module system to treat all connectives and quantifiers independently. Thus, individual connectives are available for reuse when representing other logics, and we obtain the first version of a feature library from which logics can be pieced together.Our results and methods are not restricted to first-order logic and scale to a wide variety of logical systems, thus demonstrating the feasibility of comprehensively formalizing large scale representation theorems in a logical framework.     

A measure of shared information in classes of patterns

A formal definition is given for a measure of the amount of information shared by all the members of a class of patterns. We demonstrate some properties of this measure and illustrate it with several examples. In particular, we show how this measure can be used to provide insight into the patterns of variation in the amino acid sequences of proteins. We also show how the measure can be applied to statistical models of physical processes.     

Investigating online information disclosure: Effects of information relevance,trust and risk

Organizations rely on customer information to design new products and offer new services. However, people should not share their personal information online. We produced and tested a model of information disclosure. While prior work focused on the effects of trust and its relationship to risk in determining intent to disclose information, we assumed that information relevance was a critical antecedent to disclosure and that both relevance and trust could alleviate perceptions of risk associated with disclosure, thereby increasing peoples’ intentions to disclose information. We tested our model using 264 subjects in an experimental setting. The results showed the importance of relevance on intentions to disclose information – allowing us to draw implications for practice about voluntary information disclosure in online settings.     

Representational information: a new general notion and measure of information

In what follows, we introduce the notion of representational information (information conveyed by sets of dimensionally defined objects about their superset of origin) as well as an original deterministic mathematical framework for its analysis and measurement. The framework, based in part on categorical invariance theory [30], unifies three key constructs of universal science - invariance, complexity, and information. From this unification we define the amount of information that a well-defined set of objects R carries about its finite superset of origin S, as the rate of change in the structural complexity of S (as determined by its degree of categorical invariance), whenever the objects in R are removed from the set S. The measure captures deterministically the significant role that context and category structure play in determining the relative quantity and quality of subjective information conveyed by particular objects in multi-object stimuli.     

On the use of a multi-criteria approach for reliability estimation in belief function theory

Decision analysis models often require the assessments of uncertain events elicited from informed experts to support the decision-making process. Expert opinions are often polled but their fusion is frequently beset by a number of difficulties pertaining to conflict and imperfection. Decision makers need, therefore, to reconcile inconsistencies by fusing the information provided by multiple sources of expertise. To reduce conflict and manage imperfection, expert information, represented by belief functions, need to be discounted proportionally to the degree they contribute to the conflict and its imperfection. The present study proposes a novel approach for determining the discounting operator of the information provided by a set of experts based on multiple criteria using the PROMETHEE II method. Expert judgments are then discounted and combined. Simple numerical examples and Monte Carlo simulations, including tests and comparative analysis with current approaches in the literature, are presented to illustrate the potential of the proposed approach.     

A practical information coverage approach in wireless sensor network

In order to improve energy-effectiveness in wireless sensor network, in practice some sensors in observation points are selected not to gather data. In this case, the insufficient data gathered by the rest of sensors have to cover the total network so that the complete information of the whole environment could be estimated rationally, which is similar to compressive sensing. However, the process of estimation has to cost a lot of energy, which is a crucial problem. This paper proposes a practical and effective information coverage approach in which an actual constrained condition is considered for consensus estimation to reduce unnecessary energy cost reasonably. In our experiments, the method has been proved valuable and feasible.     

Semantic enrichment of building and city information models: A ten-year review

Building Information Models (BIMs) and City Information Models (CIMs) have flourished in building and urban studies independently over the past decade. Semantic enrichment is an indispensable process that adds new semantics such as geometric, non-geometric, and topological information into existing BIMs or CIMs to enable multidisciplinary applications in fields such as construction management, geoinformatics, and urban planning. These two paths are now coming to a juncture for integration and juxtaposition. However, a critical review of the semantic enrichment of BIM and CIM is missing in the literature. This research aims to probe into semantic enrichment by comparing its similarities and differences between BIM and CIM over a ten-year time span. The research methods include establishing a uniform conceptual model, and sourcing and analyzing 44 pertinent cases in the literature. The findings plot the terminologies, methods, scopes, and trends for the semantic enrichment approaches in the two domains. With the increasing availability of data sources, algorithms, and computing power, they cross the border to enter each other’s domain. Future research will likely gain new momentums from the demands of value-added applications, development of remote sensing devices, intelligent data processing algorithms, interoperability between BIM and CIM software platforms, and emerging technologies such as big data analytics.     

Web information fusion: A review of the state of the art

In this paper, we introduce and overview advances in the field of Web information fusion and integration. As it is such a broad and diverse topic that is researched in many different fields, we choose to provide a unified view by focusing on selected survey articles that extensively cover earlier research contributions. Given the important role that ontologies are playing in Web information fusion and the emergence and fast development of the Semantic Web and Web 3.0 technologies, a separate section is devoted to the topic of ontology research and the Semantic Web. Then, in the section on Web-based support systems, several applications that are enabled as the result of advances in Web information fusion are discussed.     

Using citing information to understand the logical structure of document images

The most noticeable characteristic of a construction tender document is that its hierarchical architecture is not obviously expressed but is implied in the citing information. Currently available methods cannot deal with such documents. In this paper, the intra-page and inter-page relationships are analyzed in detail. The creation of citing relationships is essential to extracting the logical structure of tender documents. The hierarchy of tender documents naturally leads to extracting and displaying the logical structure as tree structure. This method is successfully implemented in VHTender, and is the key to the efficiency and flexibility of the whole system. Received February 28, 2000 / Revised October 20, 2000     

The role of information structures in game-theoretic multi-agent learning

Multi-agent learning (MAL) studies how agents learn to behave optimally and adaptively from their experience when interacting with other agents in dynamic environments. The outcome of a MAL process is jointly determined by all agents’ decision-making. Hence, each agent needs to think strategically about others’ sequential moves, when planning future actions. The strategic interactions among agents makes MAL go beyond the direct extension of single-agent learning to multiple agents. With the strategic thinking, each agent aims to build a subjective model of others decision-making using its observations. Such modeling is directly influenced by agents’ perception during the learning process, which is called the information structure of the agent’s learning. As it determines the input to MAL processes, information structures play a significant role in the learning mechanisms of the agents. This review creates a taxonomy of MAL and establishes a unified and systematic way to understand MAL from the perspective of information structures. We define three fundamental components of MAL: the information structure (i.e., what the agent can observe), the belief generation (i.e., how the agent forms a belief about others based on the observations), as well as the policy generation (i.e., how the agent generates its policy based on its belief). In addition, this taxonomy enables the classification of a wide range of state-of-the-art algorithms into four categories based on the belief-generation mechanisms of the opponents, including stationary, conjectured, calibrated, and sophisticated opponents. We introduce Value of Information (VoI) as a metric to quantify the impact of different information structures on MAL. Finally, we discuss the strengths and limitations of algorithms from different categories and point to promising avenues of future research.     

蒙古语语义信息词典SIKM的研发

蒙古语语义信息词典（SIKM）作为一部知识库已成为整个蒙古语语言资源的组成部分。自2009年至今,词典的研发取得了阶段性进展。SIKM现已收录5.7万多条记录,涵盖4个词典库。其中包含全部词语的1个“总库”,名词、形容词、动词等3个词类各建一个数据库。每个数据库文件都详细刻画了各词类词语及其语义属性的二维关系。目前已完成5.7万多条词语的语义分类和属性描述,该分类体系和词典的一些属性信息初步被应用到蒙古文信息处理相关基础研究和开发之中。介绍词典规模及结构,语义分类体系、属性字段描述以及研制过程中遇到的一些难点,词典的初步应用情况等内容。     

A meaning based information theory - informalogical space: Basic concepts and convergence of information sequences

This paper presents an information theory that is based on meanings and relationships between information. It first introduces the foundation of our approach, a binary relation contain between two pieces of information, based on inference between the two pieces of information. Then, based on the contain relation, it introduces two basic operations union and intersection on a collection (i.e., set) of information.This paper lays the foundation of our approach by introducing the core concept, informalogical space. An informalogical space is a collection of information that satisfies certain conditions represented in terms of the contain relation, and the union and intersection operations. An informalogical space is similar to a topological space in a symbolic sense, but is different in nature.This paper also introduces an information net in an informalogical space. An information net is a generalization of information sequence, just as a net is a generalization of sequence in general topology. This paper builds a convergence theory for information nets that is similar in a symbolic sense to the Moore-Smith convergence theory in general topology. Then, this paper applies the results for information nets to information sequences.     

Recall and Reasoning—an information theoretical model of cognitive processes

Cognitive Psychology studies humans’ capabilities to memorize and recall knowledge and images, among others. Connectionistic, propositional and conceptual models are a means to survey these phenomenons. This paper proposes an information theoretical network for simulating stimulus and response in categorical structures. A stimulus triggers an information flow throughout the whole network and generates for all ideas representing vertices an impact in the information theoretical unit [bit], thus measuring the recall intensity and producing a response. The method is shown to yield results of high performance even for complex taxonomies and connectionistic models. Reasoning is the logical counterpart of recall. Once an idea is associated with a stimulus, logical dependencies between both must be established, if required. Information theoretical networks allow to switch between a recall mode and a reasoning mode, also permitting logical reasoning within the same framework. Both capabilities are demonstrated by suitable examples.     

Belief, information acquisition, and trust in multi-agent systems—A modal logic formulation

In this paper, we consider the influence of trust on the assimilation of acquired information into an agent's belief. By use of modal logic, we semantically and axiomatically characterize the relationship among belief, information acquisition and trust. The belief and information acquisition operators are respectively represented by KD45 and KD normal modalities, whereas trust is denoted by a modal operator with minimal semantics. One characteristic axiom of the basic system is if agent i believes that agent j has told him the truth of p and he trusts the judgement of j on p, then he will also believe p. In addition to the basic system, some variants and further axioms for trust and information acquisition are also presented to show the expressive richness of the logic. The applications of the logic to computer security and database reasoning are also suggested by its connection with some previous works.     

色噪声激励下三势阱系统逻辑随机共振研究

本文利用基于Simulink的数值模拟方法研究了高斯色噪声激励下三势阱系统的逻辑随机共振现象.首先对于独立的加性和乘性高斯色噪声激励下的三势阱系统,发现仅有加性噪声作用不能实现可靠的逻辑操作,但加性噪声和乘性噪声共同作用可诱导良好的逻辑随机共振现象.和高斯白噪声相比较,高斯色噪声激励下能产生可靠逻辑随机共振的（D,Q）平面上的区域范围更大.进一步讨论了加性和乘性噪声之间的关联对于逻辑随机共振现象的影响,发现噪声关联对逻辑随机共振现象起着破坏性的作用.     

Landscaping the information space of large multi-database networks

The promises of network-accessible information are increasingly difficult to achieve. These difficulties are due to a variety of causes, such as, the rapid growth in the volume of network-available information and the increasing complexity, diversity and terminological fluctuations of the different information sources available. This paper presents a conceptual architecture for the organization information space across collections of component systems in a multi-database network that provides serendipity, exploration and contextualisation support so that users can achieve logical connections between concepts they are familiar with and schema terms employed in multi-database systems. Large-scale searching for multi-database schema information is guided by a combination of lexical, structural and semantic aspects of schema terms in order to reveal more meaning both about the contents of an information term and about its placement within the distributed information space.