Design of ontology mapping framework and improvement of similarity computation

Ontology heterogeneity is the primary obstacle for interoperation of ontologies. Ontology mapping is the best way to solve this problem. The key of ontology mapping is the similarity computation. At present, the method of similarity computation is imperfect. And the computation quantity is high. To solve these problems, an ontology-mapping framework with a kind of hybrid architecture is put forward, with an improvement in the method of similarity computation. Different areas have different local ontologies. Two ontologies are taken as examples, to explain the specific mapping framework and improved method of similarity computation. These two ontologies are about classes and teachers in a university. The experimental results show that using this framework and improved method can increase the accuracy of computation to a certain extent. Otherwise, the quantity of computation can be decreased.

Chinese Fuzzy Ontology Mapping Based on Support Vector Machine

Taking into account that fuzzy ontology mapping has wide application and cannot be dealt with in many fields at present,a Chinese fuzzy ontology model and a method for Chinese fuzzy ontology mapping are proposed.The mapping discovery between two ontologies is achieved by computing the similarity between the concepts of two ontologies.Every concept consists of four features of concept name,property,instance and structure.First,the algorithms of calculating four individual similarities corresponding to the four features are given.Secondly,the similarity vectors consisting of four weighted individual similarities are built,and the weights are the linear function of harmony and reliability.The similarity vector is used to represent the similarity relation between two concepts which belong to different fuzzy ontolgoies.Lastly,Support Vector Machine(SVM) is used to get the mapping concept pairs by the similarity vectors.Experiment results are satisfactory.

A Parsing Graph-based Algorithm for Ontology Mapping

Ontology mapping is a critical problem for integrating the heterogeneous information sources. It can identify the elements corresponding to each other. At present, there are many ontology mapping algorithms, but most of them are based on database schema. After analyzing the similarity and difference of ontology and schema, we propose a parsing graph-based algorithm for ontology mapping. The ontology parsing graph （OP-graph） extends the general concept of graph, encodes logic relationship, and semantic information which the ontology contains into vertices and edges of the graph. Thus, the problem of ontology mapping is translated into a problem of finding the optimal match between the two OP-graphs. With the definition of a universal measure for comparing the entities of two ontoiogies, we calculate the whole similarity between the two OP-graphs iteratively, until the optimal match is found. The results of experiments show that our algorithm is promising.

Ontology-based question expansion for question similarity calculation

A new ontology-based question expansion （OBQE） method is proposed for question similarity calculation in a frequently asked question （FAQ） answering system. Traditional question similarity calculation methods use ＂word＂ to compose question vector, that the semantic relations between words are ignored. OBQE takes the relation as an important part. The process of the new system is：① to build two-layered domain ontology referring to WordNet and domain corpse;② to expand question trunks into domain cases;③ to use domain case composed vector to calculate question similarity. The experimental result shows that the performance of question similarity calculation with OBQE is being improved.

Utilizing Statistical Semantic Similarity Techniques for Ontology Mapping——with Applications to AEC Standard Models

The objective of this paper is to introduce three semi-automated approaches for ontology mapping using relatedness analysis techniques. In the architecture, engineering, and construction (AEC) industry, there exist a number of ontological standards to describe the semantics of building models. Although the standards share similar scopes of interest, the task of comparing and mapping concepts among standards is challenging due to their differences in terminologies and perspectives. Ontology mapping is therefore necessary to achieve information interoperability, which allows two or more information sources to exchange data and to re-use the data for further purposes. The attribute-based approach, corpus-based approach, and name-based approach presented in this paper adopt the statistical relatedness analysis techniques to discover related concepts from heterogeneous ontologies. A pilot study is conducted on IFC and CIS/2 ontologies to evaluate the approaches. Preliminary results show that the attribute-based approach outperforms the other two approaches in terms of precision and F-measure.

一种基于语义的Ontology映射方法

O n to logy映射是实现异构O n to logy互操作的有效方法,目前的O n to logy映射主要采用句法方法,而很少采用语义方法。本文提出了一种基于语义的O n to logy映射方法,该方法考虑了O n to logy中的概念属性,采用概念名称相似性、概念属性集合相似性、相关概念集合相似性等确定O n to logy之间的语义映射关系;采用语义半径提高了语义映射方法的灵活性。试验分析表明:该方法得到的映射的准确率和查全率在90%以上,准确率和查全率均优于S-M atch方法。该方法已在基于知识需求的主动式知识系统原型中实现,并在某研究所得到了应用。

SVM-based Ontology Matching Approach

There are a lot of heterogeneous ontologies in semantic web, and the task of ontology mapping is to find their semantic relationship. There are integrated methods that only simply combine the similarity values which are used in current multi-strategy ontology mapping. The semantic information is not included in them and a lot of manual intervention is also needed, so it leads to that some factual mapping relations are missed. Addressing this issue, the work presented in this paper puts forward an ontology matching approach, which uses multi-strategy mapping technique to carry on similarity iterative computation and explores both linguistic and structural similarity. Our approach takes different similarities into one whole, as a similarity cube. By cutting operation, similarity vectors are obtained, which form the similarity space, and by this way, mapping discovery can be converted into binary classification. Support vector machine (SVM) has good generalization ability and can obtain best compromise between complexity of model and learning capability when solving small samples and the nonlinear problem. Because of the said reason, we employ SVM in our approach. For making full use of the information of ontology, our implementation and experimental results used a common dataset to demonstrate the effectiveness of the mapping approach. It ensures the recall ration while improving the quality of mapping results.

An Information Content and Set of Common Superconcepts-Based Algorithm to Estimate Similarity between Concepts of Ontologies

Ontologies have been used for several years in life sciences to formally represent concepts and reason about knowledge bases in domains such as the semantic web, information retrieval and artificial intelligence. The exploration of these domains for the correspondence of semantic content requires calculation of the measure of semantic similarity between concepts. Semantic similarity is a measure on a set of documents, based on the similarity of their meanings, which refers to the similarity between two concepts belonging to one or more ontologies. The similarity between concepts is also a quantitative measure of information, calculated based on the properties of concepts and their relationships. This study proposes a method for finding similarity between concepts in two different ontologies based on feature, information content and structure. More specifically, this means proposing a hybrid method using two existing measures to find the similarity between two concepts from different ontologies based on information content and the set of common superconcepts, which represents the set of common parent concepts. We simulated our method on datasets. The results show that our measure provides similarity values that are better than those reported in the literature.

A Survey on Semantic Similarity Measures between Concepts in Health Domain

The similarity between biomedical terms/concepts is a very important task for biomedical information extraction and knowledge discovery. The measures and tests are tools used to define how to measure the goodness of ontology or its resources. The semantic similarity measuring techniques can be classified into three classes: first, measuring semantic similarity using ontology/ taxonomy;second, using training corpora and information content and third, combination between them. Some of the semantic similarity measures are based on the path length between the concept nodes as well as the depth of the LCS node in the ontology tree or hierarchy, and these measures assign high similarity when the two concepts are in the lower level of the hierarchy. However, most of the semantic similarity measures can be adopted to be used in health domain (Biomedical Domain). Many experiments have been conducted to check the applicability of these measures. In this paper, we investigate to measure semantic similarity between two concepts within single ontology or multiple ontologies in UMLS Metathesaurus (MeSH, SNOMED-CT, ICD), and compare my results to human experts score by correlation coefficient.

基于节点语义相似度的本体映射方法

针对本体映射特别是大尺度的异构本体映射由于语义异质性导致的映射精度和效率较低的问题,提出一种基于节点语义相似度的本体映射方法.首先,研究基于网络的本体解析和表示、本体自动分块、相似子本体快速识别、基于节点语义的子本体映射等关键技术;其次,以本体对齐评估倡议评估数据集中会议本体集进行实验,结果表明,该方法在性能上优于传统映射方法,在精度上高于基于片段的映射方法.

数智化背景下基于本体驱动的工业互联网平台信息融合研究

[目的/意义]数智化时代,如何实现多源信息的有效融合是工业互联网平台在高效组织并利用信息的过程中亟须重视的问题。[方法/过程]针对工业互联网平台中多源异构的信息,文章提出一种基于本体的信息融合框架。首先构建工业互联网平台信息本体,实现对领域知识统一规范的描述;然后设置融合规则和过程,通过本体映射,利用GA-SA-BP算法计算本体概念综合相似度,获得平台信息本体与基于数据源的局部本体之间的映射结果;最后依据映射结果和融合规则实现工业互联网平台多源信息的融合。[结果/结论]以航天云网INDICS平台中的信息资源为例进行验证,所提的信息融合方法能实现多源异构信息的融合,对工业互联网平台信息资源的集成化管理和应用具有一定的参考价值。

本体中概念相似度的计算

本体是概念、属性和关系的集合。本体异构是本体间互操作的主要障碍,解决本体异构最好的方法是本体映射。本体映射的关键是概念相似度的计算,但计算时一般不考虑关系和属性对相似度的影响,计算结果存在误差。论文从两个方面对概念的相似度进行计算。首先计算概念的语义相似度,然后计算概念描述相似度。实验表明该计算方式可以提高计算结果的精确度。

一个基于相似度计算的动态多维概念映射算法

本体作为一种领域知识结构化描述和推理的基础已经获得广泛认可.然而,本体本身是异构的.特别在多Agent系统、语义网、知识管理等开放环境下,如何协调不同领域的本体,甚至是同领域的本体的语义差异是一个基本问题.本文以相似度计算为基本思想提出了一个多维动态的概念映射算法S-Match.该算法可以根据不同的灵活性和准确性需求,在语言级、结构级、实例级和推理级四个维度上动态地进行本体概念映射.初步试验结果表明,S-Match算法在查全率和查准率方面要优于H-Match算法,并且比GLUE方法要求更少的专业知识支持.

一种本体概念的语义相似度计算方法

概念语义相似度已广泛应用于Web服务发现、本体映射等领域,但现有的概念语义相似度计算方法对概念间语义相似程度的区分不够细致.本文从本体结构出发,首先提出了自底向上的本体概念出现概率计算方法,并在此基础上改进了基于节点信息量的概念语义相似性度量方法;然后又设计了基于边计算的本体概念语义相似度计算方法;最后对上述两种方法线性加权,提出了一种加权的本体概念语义相似度计算方法.实验结果表明该方法能进一步正确区分本体中父子概念及兄弟概念间的相似程度.

一种综合的本体相似度计算方法

本体相似度计算是本体映射的关键环节。本体的实例、关系、属性、结构等信息是相似度计算需要考虑的重要因素。针对目前本体映射过程中相似度计算所存在的问题,提出了一种综合的相似度计算方法。首先判断不同本体之间是否存在相关性。若相关,则充分考虑各种相关因素,从语义和概念两个层面来进行比较,然后给出了本体的综合相似度计算方法。最后采用了两组测试数据对该方法进行实验,并与GLUE系统的概率统计方法进行了实验对比。实验结果表明,该方法能够有效确保相似度计算的准确性。

领域本体中的概念相似度计算

借鉴计算语言学中的语义距离思想,提出了RDFSchema构词所描述的本体概念相似度计算方法,并利用该方法对农业知识本体(AO)所描述的部分概念进行了相似度计算和分析.结果表明,该方法可以定量地分析概念、特性之间的相似度,并可以指导基于领域知识本体的语义查询中的概念集扩充和查询结果排序.

基于本体概念相似度的语义Web服务匹配算法

通过定义本体中概念之间的语义距离来计算本体概念之间的相似度,提出一种基于该相似度的Web服务的精确匹配算法,新的算法与经典的OWL-S/UDDI匹配算法比较,不仅在等级上保持一致,而且使同一等级或不同等级之间的服务匹配都达到精确的程度。用GEIS系统中Web服务的数据进行两种算法的性能测试,得出相似度匹配算法的平均查准率是OWL-S/UDDI匹配算法的1.8倍,平均查准率是OWL-S/UDDI匹配算法的1.4倍。

一种改进的本体语义相似度计算及其应用

词语相似度研究,是知识表示以及信息检索领域中的一个重要内容。词语相似度的计算方法一般是利用大规模的语料库来统计。本体给词语间相似度计算带来了新的机会。利用本体结构上的ISA关系,提出了本体内部概念之间的相似度计算方法。实验结果表明,该方法能充分利用本体特点来计算相关概念之间的相似度。结合一个简单本体,介绍了如何计算概念间的相似度,及其在智能检索系统中的应用。

基于本体的概念相似度计算

概念相似度的计算是信息检索领域的研究热点。本体在信息检索和人工智能领域的广泛应用,为概念相似度计算带来新的方法。该文提出一种利用本体来计算概念间相似度的方法,综合考虑语义距离和本体库统计特征。加入概念的深度、语义重合度和概念间强度的辅助影响。实验结果表明,该方法对概念相似度的计算有效,可应用于面向Web的信息检索。