• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.04a
• /
• pp.664-667
• /
• 2014

기존 온톨로지들을 공유 및 재사용하기 위하여 온톨로지 정렬이 연구되고 있다. 기존 정렬 시스템은 온톨로지 데이터 양에 따라 매트릭스를 생성하고 과도한 계산을 통해 처리하여 대용량 데이터 집합에 대하여 공간적 및 계산적으로 부하를 발생하여 효율적이지 않다. 이를 해결하기 위하여 온톨로지 정렬을 휴리스틱 알고리즘을 적용하여 연구 진행하였다. 기존 휴리스틱 알고리즘은 계산이 간단하지만 조율해야 하는 파라미터가 많기에 특정 도메인에 최적 조합이 필요하며 만족한 성능을 얻지 못하였다. 이 논문에서는 Discrete Cuckoo Search(DCS) 기반 온톨로지 정렬 알고리즘을 제안한다. 제안한 알고리즘은 조율해야 하는 파라미터의 개수가 적고 Levy Flight 분포에 따라 탐색하여 계산이 간단하다. 제안된 알고리즘의 성능을 평가하기 위해 OAEI(Ontology Alignment Evaluation Initiative)에서 제공하는 벤치마크 데이터를 사용하여 정확률(Precision)과 재현율(Recall)을 구하고 기존 휴리스틱 정렬 알고리즘과 비교 평가하였다.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.12
• /
• pp.523-530
• /
• 2014

Ontology alignment is the way to share and reuse of ontology knowledge. Because of the ambiguity of concept, most ontology alignment systems combine a set of various measures and complete enumeration to provide the satisfactory result. However, calculating process becomes more complex and required time increases exponentially since the number of concept increases, more errors can appear at the same time. Lately the focus is on meta-matching using the heuristic algorithm. Existing meta-matching system tune extra parameter and it causes complex calculating, as a consequence, the results in the various data of specific domain are not good performed. In this paper, we propose a high performance algorithm by using DCS that can solve ontology alignment through simple process. It provides an efficient search strategy according to distribution of Levy Flight. In order to evaluate the approach, benchmark data from the OAEI 2012 is employed. Through the comparison of the quality of the alignments which uses DCS with state of the art ontology matching systems.

• Journal of the Korean Society for information Management
• /
• v.26 no.4
• /
• pp.319-336
• /
• 2009

Semantic web technology is the evolution of current World Wide Web including a machine-understandable knowledge database, ontology, it may be enable machine and people to work together. However, problems arise when we try to communicate with different data, which are annotated by different ontologies created by different people with different concepts. Thus, to communicate between ontologies, it needs to align between heterogeneous ontologies. When it is aligned between concept nodes of heterogeneous ontologies, one of main problems is a misalignment situation caused by false negative of automatic ontology mapping. So, in this paper, we present a new method to minimize the false negative error in the process of aligning concept nodes of different ontology.

• Journal of KIISE:Software and Applications
• /
• v.36 no.4
• /
• pp.329-334
• /
• 2009

The ontology alignment has two kinds of major problems. First, the features used for ontology alignment are usually defined by experts, but it is highly possible for some critical features to be excluded from the feature set. Second, the semantic and the structural similarities are usually computed independently, and then they are combined in an ad-hoc way where the weights are determined heuristically. This paper proposes the modified parse tree kernel (MPTK) for ontology alignment. In order to compute the similarity between entities in the ontologies, a tree is adopted as a representation of an ontology. After transforming an ontology into a set of trees, their similarity is computed using MPTK without explicit enumeration of features. In computing the similarity between trees, the approximate string matching is adopted to naturally reflect not only the structural information but also the semantic information. According to a series of experiments with a standard data set, the kernel method outperforms other structural similarities such as GMO. In addition, the proposed method shows the state-of-the-art performance in the ontology alignment.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.4
• /
• pp.23-30
• /
• 2004

Ontologies play an important role in the Semantic Web by providing well-defined meaning to ontology consumers. But as the ontologies are authored in a bottom-up distributed mimer, a large number of overlapping ontologies are created and used for the similar domains. Ontology sharing and reuse have become a distinguished topic, and ontology merging and alignment are the solutions for the problem. Ontology merging and alignment algorithms previously proposed detect conflicts between concepts by making use of only local syntactic information of concept names. And they depend only on a semi-automatic approach, which makes ontology engineers tedious. Consequently, the quality of merging and alignment tends to be unsatisfying. To remedy the defects of the previous algorithms, we propose a new algorithm for ontology merging and alignment which uses local and global semantic set of a concept. We evaluated our algorithm with several pairs of ontologies written in OWL, and achieved around 91% of precision in merging and alignment. We expect that, with the widespread use of web ontology, the need for ontology sharing and reuse ill become higher, and our proposed algorithm can significantly reduce the time required for ontology development. And also, our algorithm can easily be applied to various fields such as ontology mapping where semantic information exchange is a requirement.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.169-171
• /
• 2006

인터넷이 보다 대중화되고 광범위해지면서 의미적 관계에 따라 정보를 저장하는 온톨로지 시스템이 미래의 지능적인 컴퓨터를 위한 적절한 수단으로 각광받고 있다. 하지만 온톨로지와 같은 메타 데이터를 사용한 방법은 그 사용 목적 또는 작성자의 개인적인 관점에 따라 다양한 이질적인(heterogeneous) 형태를 띠게 된다. 이러한 이질적인 정보들은 데이터가 다른 시스템에서 처리되는 것을 어렵게 한다. 정보의 상호운용성을 보장하기 위해서는 서로 다른 온톨로지 시스템간의 개체에 대한 유사도를 평가할 수 있어야 한다. 따라서 두 개의 다른 OWL 언어로 정의된 온톨로지 사이에서 두 개의 엔티티의 유사도를 측정하기 위한 새로운 유사도 척도(similarity measure)를 제안하였다. 이는 온톨로지 상의 이질적인 정보를 통합하는데 사용되며, 온톨로지 비교(comparison), 정렬(alignment), 매칭(matching) 그리고 병합(merging)의 기반이 되는 중요한 기법이다. 새로운 유사도 척도는 특정한 매핑 정보를 사용하지 않고 온톨로지 언어의 속성을 기반으로 하므로 OWL을 사용한 온톨로지 간의 유사도 검색에 곧바로 적용될 수 있는 장점을 지닌다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.11a
• /
• pp.72-73
• /
• 2010

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.3
• /
• pp.571-576
• /
• 2024

Ontologies are created by domain experts, but the same content may be expressed differently by each expert due to different understandings of domain knowledge. Since the ontology standardization is still lacking, multiple ontologies can be exist within the same domain, resulting in a phenomenon called the ontology heterogeneity. Therefore, we propose a novel ontology matching method that combines SCBOW(: Siames Continuois Bag Of Words) and BERT(: Bidirectional Encoder Representations from Transformers) models to solve the ontology heterogeneity issue. Ontologies are expressed as a graph and the SimRank algorithm is used to solve the one-to-many problem that can occur in ontology matching problems. Experimental results showed that our approach improves performance by about 8% over traditional matching algorithm. Proposed method can enhance and refine the alignment technology used in ontology matching.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06a
• /
• pp.104-105
• /
• 2008

• 한국어정보학회:학술대회논문집
• /
• 2016.10a
• /
• pp.313-316
• /
• 2016

온톨로지란 사물이나 개념의 속성이나 관계를 사람과 컴퓨터 모두 이해할 수 있는 형태로 표현한 모델로 정보검색, 인공지능, 소프트웨어 공학 등의 분야에서 많이 활용된다. 온톨로지에는 다양한 정보가 구조화되어 저장되어 있지만 일반적으로 온톨로지가 제공하는 그래프 형태의 데이터들은 사용자들이 직관적으로 이해하기가 힘들다. 따라서 본 논문에서는 온톨로지의 정보를 문장화하여 한국어 문서를 생성하는 시스템을 제안한다. 제안하는 시스템은 주제와 관련된 트리플을 추출하고 이를 문장정렬, 결합, 생성을 위한 정보가 담긴 템플릿을 생성한 뒤 한국어 문법에 맞게 문장을 생성한다. 또한 기존 연구에서 다루지 않았던 이벤트 온톨로지의 내용을 포함하여 문장을 생성한다. 두 온톨로지로부터 생성된 문장을 연결하여 주제어를 설명하는 하나의 문서를 작성한다.