A Terminological Search Algorithm for Ontology Matching

2009

A set of ontology matching algorithms (for finding correspondences between concepts) is based on a thesaurus that provides the source data for the semantic distance calculations. In this wiki era, new resources may spring up and improve this kind of semantic search. In the paper a solution of this task based on Russian Wiktionary is compared to WordNet based algorithms. Metrics are estimated using the test collection, containing 353 English word pairs with a relatedness score assigned by human evaluators. The experiment shows that the proposed method is capable in principle of calculating a semantic distance between pair of words in any language presented in Russian Wiktionary. The calculation of Wiktionary based metric had required the development of the open-source Wiktionary parser software.

Indonesian Journal of Electrical Engineering and Computer Science, 2017

Ontology matching is a discipline that means two things: first, the process of discovering correspondences between two different ontologies, and second is the result of this process, that is to say the expression of correspondences. This discipline is a crucial task to solve problems merging and evolving of heterogeneous ontologies in applications of the Semantic Web. This domain imposes several challenges, among them, the selection of appropriate similarity measures to discover the correspondences. In this article, we are interested to study algorithms that calculate the semantic similarity by using Adapted Lesk algorithm, Wu & Palmer Algorithm, Resnik Algorithm, Leacock and Chodorow Algorithm, and similarity flooding between two ontologies and BabelNet as reference ontology, we implement them, and compared experimentally. Overall, the most effective methods are Wu & Palmer and Adapted Lesk, which is widely used for Word Sense Disambiguation (WSD) in the field of Automatic Natural ...

2019

In the areas of Semantic Web and data integration, ontology matching is one of the important steps to resolve semantic heterogeneity. Manual ontology matching is very labor-intensive, time-consuming and prone to errors. So development of automatic or semi-automatic ontology matching methods and tools is quite important. This paper applies machine learning with different similarity measures between ontology elements as features for ontology matching. An approach to combine string-based, language-based and structurebased similarity measures with machine learning techniques is proposed. Logistic Regression, Random Forest classifier and Gradient Boosting are used as machine learning methods. The approach is evaluated on two datasets of Ontology Alignment Evaluation Initiative (OAEI).

Ontology matching is a main step for integrating overlapping domains of knowledge and establishing interoperation among semantic web application. As information sources grow rapidly, manual ontology matching becomes more tedious and time-consuming and consequently leads to errors and frustration. In this paper we developed the new lexical and semantic similarity measure by using the lexical database ConceptNet. The proposed strategy used new lexical and semantic matching for finding the correspondence entities. In the semantic approach we use the electronic lexical database, ConceptNet for identifying the similar entities and create similarity matrices according to that. We evaluate the proposed measure using standard methods of precision and recall, tested on a well-known benchmark and also compared to other algorithms presented in the paper. The experimental results show the proposed algorithm is effective and outperforms other algorithms.

Proceedings of the 9th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, 2017

The identification of alignments between heterogeneous ontologies is one of the main research issues in the semantic web. The manual matching of the ontologies is a complex, time consuming and an error prone task. Therefore, ontology matching systems aims to automate this process. Usually, these systems perform the matching process by combining element and structural level matchers. Selecting the optimal string similarity measure associated with its threshold is an important issue in order to enhance the effectiveness of the element level matcher, which in turn will improve the whole ontology system results. In this paper, we present POMap, an ontology matching system based on a syntactic study covering element and structural levels. For the element level matcher we have adopted the best configuration based on the analysis of the performances of many string similarity measures associated with their thresholds. For the structural level, we have performed a syntactic study on both subclasses and siblings in order to infer the structural similarity. Our proposed matching system is validated and evaluated on the Anatomy, the Conference and the Large Biomedical tracks provided by the benchmark of OAEI 2016 ontology matching campaign.

2006

several methods have been suggested for Ontology Alignment problem, each exploits some measures and uses of their combinations in order to come up with higher quality of alignment. A group of such measures are especially based on structural position of the entities in ontologies, the corresponding measures of which are named Structural Measures. This paper is about to present a new method for computing Structural Similarity, based on the notion of Information Content. The method employs various aspects of the structure of ontologies to recognize related entities. We evaluate the proposed measure using standard methods of Precision and Recall, as well as a new one based on Sensitivity Analysis from Data Mining. Evaluation results show superiority of proposed structural measure over the rest of the methods taking part in the presented tests.

International Journal of Engineering & Technology

Heterogeneity in documents is a challenge for information Retrieval. The keyword search focuses on matching the keywords with web repositories. It does not consider the synonyms or semantically similar words. The heterogeneity of the content makes retrieval inadequate. Semantic search helps to capture more appropriate results using domain ontology. Keyword search is extended with the help of similar concepts of ontology. Similarity between the ontological concepts is recognized to get appropriate search results. Once the semantic similarity among the concepts is known, more relevant documents can be retrieved. In this paper, we propose a metric based on traditional methods, combined with computational techniques to measure the similarity between concepts. The paper gives the concept of DOT (Domain Ontology Tree). It uses conventional definitions of the Tree (Data Structure) for ontology and proposes a method of partitioning to calculate the similarity. The method is based on IS-A hi...

2015

Ontology is the main infrastructure of the Semantic Web which provides facilities for integration, searching and sharing of information on the web. Development of ontologies as the basis of semantic web and their heterogeneities have led to the existence of ontology matching. By emerging large-scale ontologies in real domain, the ontology matching systems faced with some problem like memory consumption. Therefore, partitioning the ontology was proposed. In this paper, a new clustering method for the concepts within ontologies is proposed, which is called SeeCC. The proposed method is a seeding-based clustering method which reduces the complexity of comparison by using clusters’ seed. The SeeCC method facilitates the memory consuming problem and increases their accuracy in the large-scale matching problem as well. According to the evaluation of SeeCC's results with Falcon-AO and the proposed system by Algergawy accuracy of the ontology matching is easily observed. Furthermore, co...

Improvements made to the algorithm COM of Olivares are presented. Such algorithm finds the concept c B in ontology B most closely resembling a given concept c A in ontology A. It also finds the similarity between both concepts. Our improvements significantly complete it and increase its accuracy. They consist of: (1) a better notation for ontologies; (2) representation of partitions;

2012

Ontology matching is the process of finding correspondences between semantically related entities of different ontologies. We need to apply this process to solve the heterogeneity problems between different ontologies. Some ontologies may contain thousands of entities which make the ontology matching process very complex in terms of space and time requirements. This paper presents a framework that reduces the search space by removing entities (classes, properties) that have less probability of being matched. In order to achieve this goal we have introduced a matching strategy that uses multi matching techniques specifically; string, structure, and linguistic matching techniques. The results obtained from this framework have indicated a good quality matching outcomes in a low time requirement and a low search space in comparisons with other matching frameworks. It saves from the search space from (43%-53%), and saves on the time requirement from (38%-45%).