Multiagent Approach to Coreference Resolution Based on the Multifactor Similarity in Ontology Population

The multiagent approach to coreference resolution in the process of extracting information from texts in natural languages for ontology population is described. Special class agents corresponding to ontology classes are defined. They analyze the available information in the corresponding ontology instances. The results of this analysis are used for values to instance attribute, for detecting duplicates and equivalents of instances, for fixing coreferential relations, and for determining the weights of information connections used to resolve ambiguities. Coreferences are resolved taking into account a multifactor similarity measure between extracted objects that combines the semantic, context, positional, and grammar similarity measures. The class agents work within the multiagent approach to text analysis aimed at ontology population.     

改进的本体概念相似度计算模型

本体映射能很好地解决语义网中的本体异构性问题,其核心在于计算本体概念的相似度。针对现有的概念相似度计算的精度和查准率不高,提出一种改进的概念相似度计算模型。首先利用本体特征之间的偏序关系建立形式背景和概念格,然后在结构层次求出概念间的交不可约元集,并通过对集合里各元素的语义关系进行量化计算出概念间的相似度。实例和分析结果表明,改进的概念相似度计算模型在F-Score上有明显提高。     

An adaptive ontology mapping approach with neural network based constraint satisfaction

Ontology mapping seeks to find semantic correspondences between similar elements of different ontologies. It is a key challenge to achieve semantic interoperability in building the Semantic Web. This paper proposes a new generic and adaptive ontology mapping approach, called the PRIOR+, based on propagation theory, information retrieval techniques and artificial intelligence. The approach consists of three major modules, i.e., the IR-based similarity generator, the adaptive similarity filter and weighted similarity aggregator, and the neural network based constraint satisfaction solver. The approach first measures both linguistic and structural similarity of ontologies in a vector space model, and then aggregates them using an adaptive method based on their harmonies, which is defined as an estimator of performance of similarity. Finally to improve mapping accuracy the interactive activation and competition neural network is activated, if necessary, to search for a solution that can satisfy ontology constraints. The experimental results show that harmony is a good estimator of f-measure; the harmony based adaptive aggregation outperforms other aggregation methods; neural network approach significantly boosts the performance in most cases. Our approach is competitive with top-ranked systems on benchmark tests at OAEI campaign 2007, and performs the best on real cases in OAEI benchmark tests.     

HYPERTEXT-BASED REPRESENTATION OF KNOWLEDGE AND REASONING FOR USER GUIDANCE IN DIAGNOSIS OF COMPLEX SYSTEMS

ABSTRACT

The development of a hypertext-based diagnosis system requires, on one hand, adapted tools for a task oriented navigation across the documents, and on the other hand, context sensitive browsing capability of the knowledge base. This paper presents a system that possesses both properties. It is based on a formal model ontology for representing a diagnostic domain, a computational scheme to implement and use the ontology, and a human-machine interface to provide users with an efficient access to objects, methods, and relations described in the ontology. We use an example based on the diagnosis of vibrations of rotating machines throughout the paper to illustrate the approach. The example has been built and implemented according to the norm (AFNOR 1998), which defines the protocol and the evaluation procedure of vibration from signals measured and recorded on the rotating machines.     

基于形式概念分析的本体合并方法

针对现有的本体合并方法在进行合并时需要人工参与,比较费时费力,且合并结果受人为影响过大等缺点,提出了一种基于形式概念分析的本体合并方法——FCA-OntMerge(formal concept analysis based ontology merging method)。该方法首先将本体中的数据直接转化为形式背景(概念格的数据存储方式),然后利用概念格严谨和完善的数学原理进行合并,最后生成新的本体。实验结果表明,该方法能很好地解决本体异构的问题。     

Study on battlespace ontology construction approach

In Network Centric Warfare, the sensor network's capability is much stronger than ever; the force can get a mass of information about battlespace in real or near‐real time. How to utilize the information about battlespace effectively and transform the information superiority into knowledge superiority is a key problem for NCW research. To solve this problem, first we need to establish a suitable knowledge infrastructure. In this article, battlespace ontology is considered as the knowledge infrastructure of NCW, and we propose a battlespace ontology construction approach based on OWL, which consists of two parts: formal ontology construction approach to construct subdomain ontologies of battlespace and formal ontology integration approach to integrate subdomain ontologies of battlespace. Then a concrete application of the approach to an air combat battlespace is given. © 2005 Wiley Periodicals, Inc. Int J Int Syst 20: 1219–1231, 2005.     

基于粗概念格模型的电子商务领域本体的构建研究

以构建电子商务系统中的本体为出发点,分析现有的本体构建技术中存在的缺陷。针对这些不足,综合考虑变精度粗糙集模型和形式概念分析的相关理论,提出基于粗概念格模型来构建本体。将变精度粗糙集的β选取算法和可辨识矩阵属性约简算法进行了改进,使β 上、下分布的约简方法适用于形式背景的约简,从而提出基于变精度粗糙集的概念格约减算法;然后计算语义概念相似度,并以联合国标准产品与服务分类代码的本体元模型为核心本体,结合领域专家知识,建立电子商务领域本体模型。实验表明了粗概念格构建本体的高效性。     

一种综合事件本体相似度计算方法

事件本体相比于传统本体具有更加丰富的语义信息,在面向事件的大数据集成中更具优势,然而用传统的本体相似计算方法计算事件本体相似度存在很多不足,提出了一种综合的事件本体相似度计算方法。该方法以词语相似度、集合相似度、层次结构相似计算为基础,然后从事件类名称、事件类要素、事件类层次结构和非层次结构讨论事件本体的相似度,最终获得事件本体的综合相似度。实验表明该方法相比传统本体相似度计算方法准确率更高,语义信息更加丰富。     

多民族语言本体知识库构建技术

语义本体是共享概念模型的显示的形式化规范说明,其目标是将杂乱无章的信息源转变为有序易用的知识源。语义本体知识库的构建是文本自动处理的一个重要环节,跨语言信息检索、信息抽取、自动翻译等领域中都有广泛的应用。该文旨在描述统一标准、统一接口的多民族语言本体知识库的创建思路,以及包含的若干问题,例如 多民族语言中共有概念的一般表示与各民族语言特有的事物表达方式的规律,基于词汇语义的、包括汉语、英语及少数民族语言在内的多民族语言语义本体的表示理论与方法等。     

Detecting mistakes in binary data tables

We suggest a classification of possible mistakes in lines of binary data tables (in formal contexts) and discuss their detection. An approach is proposed to detect some types of mistakes in new lines (contents of objects) of binary data tables (formal contexts). This approach is based on detecting those implications from implication bases of the formal contexts that are not met by a new object. It is noted that this approach can result in a complex computational solution. An alternative approach based on computing closures of subsets of object’s intent. This approach allows one to find a polynomial algorithm for the solution. The algorithm of unnecessary and extra missing properties can also be used. The results of experiments are dealt with.     

基于FCA的对象与属性交叉渐进的情感本体学习

提出了一种基于形式概念分析的渐进式情感本体学习的算法。该算法通过动态交叉添加对象和属性来生成概念格,从而从概念格当中抽取情感本体,最终实现情感本体的学习过程。给出了算法的描述,并结合实例说明了本体学习过程。     

领域本体驱动下企业联机分析处理系统应用研究

传统联机分析处理(OLAP)系统存在着形式化业务知识参与不足的状况,对深度推理分析造成了制约和局限。为了克服上述缺点,提出一种领域本体驱动的OLAP系统构建方法。首先,通过分析现有本体构建方法的局限性,依托实体类多特征加权相似度判断算法,提出先全局设计后局部抽取的半自动本体构建模式,实现矿山生产领域知识形式化;接着在此基础上,以矿山生产能力关键指标为度量,完成负载业务概念多维本体(MDO)建模;最后,在实际矿山决策系统项目建设中,进行了方法检验。实验结果表明,该方法充分发挥领域本体形式化表达与推理优势,有效整合多源异构信息和明晰多维分析过程,实现内隐知识与关联规则深度挖掘;同时借助高频通用概念视图定义,避免重复维度建模,改进了传统OLAP效能。     

基于内涵模糊概念格的汽车评价知识发现方法研究

为了有效利用汽车评论数据,参照已建立的汽车评价本体,从文本中抽取评价搭配对,提出基于五元组的对象评价度量,从而获取汽车评价模糊形式背景。在模糊形式背景中,定义了内涵模糊概念和内涵模糊概念格。设计了模糊形式背景和内涵模糊概念格构建算法,并以实例对如何基于内涵模糊概念格进行知识发现予以讨论。     

基于差别矩阵的概念格多层次属性约简

给出形式背景新的差别矩阵,利用差别矩阵定义概念与子概念格的特征函数,得到形式背景属性协调集及概念格中存在相似概念的判定定理。采用差别矩阵和特征函数,设计计算概念与子概念格(包括概念格)属性约简的方法,通过实例表明该约简方法的可行性与有效性。     

Resolution of Semantic Heterogeneity in Database Schema Integration Using Formal Ontologies

This paper addresses the problem of handling semantic heterogeneity during database schema integration. We focus on the semantics of terms used as identifiers in schema definitions. Our solution does not rely on the names of the schema elements or the structure of the schemas. Instead, we utilize formal ontologies consisting of intensional definitions of terms represented in a logical language. The approach is based on similarity relations between intensional definitions in different ontologies. We present the definitions of similarity relations based on intensional definitions in formal ontologies. The extensional consequences of intensional relations are addressed. The paper shows how similarity relations are discovered by a reasoning system using a higher-level ontology. These similarity relations are then used to derive an integrated schema in two steps. First, we show how to use similarity relations to generate the class hierarchy of the global schema. Second, we explain how to enhance the class definitions with attributes. This approach reduces the cost of generating or re-generating global schemas for tightly-coupled federated databases.     

Variable weight semantic graph‐based ontology mapping method

The mapping method that is based on the name and structure of the ontology elements is the strategy used in most mapping methods. Methods using the name often only use the similarity between the individual elements in the ontology to predict the semantic relations between two ontologies, while the latter measure the mapping between two ontologies by means of the structural relations between the elements. The effects of these two kinds of mapping strategies are not ideal. Addressing this issue, the work presented in this paper proposes an ontology mapping approach, in which the ontology element name and structure are combined. It uses the approaches based on linguistics and distance to generate a variable weight semantic graph. On this graph, the similarity of element names and structure are calculated through iterative computation. In the process of iteration, similarity result values are constantly adjusted. The approach avoids the problem of single methods that cannot use the entire amount of ontology information; therefore, it provides a more ideal mapping result. For making full use of the message of ontology, our implementation and experimental results are provided to demonstrate the effectiveness of the mapping approach.     

基于RFID普适计算环境的形式化上下文模型

提出了一个适合普适计算环境的、基于本体的形式化的上下文感知模型。该模型使用本体描述语言OWL描述上下文,采用层次化的设计方法,提高了上下文表达能力和快速上下文原型。为普适计算的上下文建模和应用、上下文重用和建立面向普适计算环境的软件基础设施提供了一种可行的方法。     

New similarity measures of intuitionistic fuzzy sets based on the Jaccard index with its application to clustering

A similarity measure is a useful tool for determining the similarity between two objects. Although there are many different similarity measures among the intuitionistic fuzzy sets (IFSs) proposed in the literature, the Jaccard index has yet to be considered as way to define them. The Jaccard index is a statistic used for comparing the similarity and diversity of sample sets. In this study, we propose a new similarity measure for IFSs induced by the Jaccard index. According to our results, proposed similarity measures between IFSs based on the Jaccard index present better properties. Several examples are used to compare the proposed approach with several existing methods. Numerical results show that the proposed measures are more reasonable than these existing measures. On the other hand, measuring the similarity between IFSs is also important in clustering. Thus, we also propose a clustering procedure by combining the proposed similarity measure with a robust clustering method for analyzing IFS data sets. We also compare the proposed clustering procedure with two clustering methods for IFS data sets.     

基于模糊概念格的语义Web服务匹配

针对不同本体领域语Web服务匹配问题,提出基于模糊概念格模型的语义Web服务匹配方法。将不同本体映射成统一形式背景,进而形成模糊概念格结构,最后在模糊概念格结构的基础上,提出了服务的相似度计算方法。实验结果表明该服务匹配方法的有效性。