Comparing Ontologies Using Entropy

Jang, Seong-Cheol; Lee, Joo-Hwan; Lee, Jung‐Hoon; Park, Sung-Bin; Hwang, Sung-Oh; Yoon, Hyoung Ro; Yoon, Young-Ro

doi:10.1109/iccit.2007.390

Cited by 7 publications

(5 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are some indications though. Cho et al (2007) found an average entropy of 17.48 for domain ontologies in WordNet. We found for the basic-level ontology an entropy of 10.67 and for the restricted expert-based ontology without homonyms an entropy of 26.82.…”

Section: Discussionmentioning

confidence: 99%

“…The entropy of an ontology can be computed by taking the number of relations a concept has and sum over the probabilities of these relations (Calmet & Daemi, 2004;Cho et al, 2007;Doran et al, 2009;Resnik, 1995Resnik, , 1999. It is a measure based on the information content of an ontology (Scharrenbach et al, 2010;Coskun et al, 2011;Palmisano et al, 2009).…”

Section: Entropymentioning

confidence: 99%

“…It is a measure based on the information content of an ontology (Scharrenbach et al, 2010;Coskun et al, 2011;Palmisano et al, 2009). Cho et al take entropy to be the ambiguity caused by the number of subsumption relations a concept has (Cho et al, 2007). The informational content of a concept i is measured as the ratio of the number of all members of a concepts subtree (including itself) |Φ i | to the total set of concepts |Ω|.…”

Section: Entropymentioning

confidence: 99%

See 2 more Smart Citations

Engineering ontologies for question answering

et al. 2014

View full text Add to dashboard Cite

Using an ontology to automatically generate questions for ordinary people requires a structure and concepts compliant with human thought. Here we present methods to develop a pragmatic, expert-based and a basic-level ontology and a framework to evaluate these ontologies. Comparing these ontologies shows that expert-based ontologies are most easy to construct but lack required cognitive semantic characteristics. Basic-level ontologies have structure and concepts which are better in terms of cognitive semantics but are most expensive to construct.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Entropymentioning

confidence: 99%

Section: Entropymentioning

confidence: 99%

See 1 more Smart Citation

Engineering ontologies for question answering

et al. 2014

View full text Add to dashboard Cite

show abstract

“…Here, a probabilistic generalization is created for each data point within the set, and the lengths of each node is generated based on the probability of a given node [column]. As nodes in the hierarchical structure increase, the overall information representation increases in tandem [19]. Algorithm 4 presents our method for producing the intersections found in our ontological representation of the mixed data-type dataset, as seen in 6. , where the final fraction will be raised to a measured coefficient power end end end…”

Section: B Completeness Graphingmentioning

confidence: 99%

Machine Learning Analysis for Data Incompleteness (MADI): Analyzing the Data Completeness of Patient Records Using a Random Variable Approach to Predict the Incompleteness of Electronic Health Records

Gurupur

Shelleh

2021

IEEE Access

View full text Add to dashboard Cite

The purpose of this article is to propose a methodology involving various methods that can be used to predict the data incompleteness of a dataset. Here the investigators have presented data incompleteness as both a continuous and discrete random variables and transfer entropy for the purpose of advancing the science associated with the analysis of data incompleteness of electronic health records. The underlying methodology has been coined as "Machine Learning Analysis for Data Incompleteness" (MADI) with the intention of developing a possible solution to data incompleteness in electronic health records. MADI advances the analysis of data incompleteness with the use of Kolomogorov Smirnov goodness of fit, mielke distribution, and beta distributions for a holistic analysis. Alongside the methodology presented, the investigators explored stochastic gradient descent, generalized additive models, and support vector machines for comparison. Overall, the investigators have presented a complete set of methods and algorithms to help predict data incompleteness in a medical setting and provided suggestions for practical applications into the prediction of data incompleteness.

show abstract

“…Distance between two concepts is a numerical representation of how far apart two concepts are from one another in some geometric space, and can be considered the inverse of semantic similarity [15]. The paper [4] compared ontologies using entropy which shows structural features of ontology as the average of information content. However, these two kinds of method have their own limitations.…”

Section: Computing Semantic Similaritymentioning

confidence: 99%

Improving Query Suggestion for Digital Libraries

Chao

Zhang

Xing

2011

2011 IEEE 35th Annual Computer Software and Applications Conference Workshops

View full text Add to dashboard Cite

The users of a digital library often have difficulty in formulating query expression that could represent his or her information requirements exactly. Query suggestion can provide some recommended query expression and help the user build a proper expression. Query suggestion for digital libraries requires higher precision ratio and novelty ratio than that of web search engines. Based on case studies, we found that there are four main types of query suggestion within digital library environments, namely spelling suggestion, hot keyword suggestion, personalized suggestion and semantic suggestion. These approaches are, however, hardly to ensure high precision ratio and novelty ratio expected by digital library users to date. The paper proposed an improved query suggestion approach for digital library and its main advantages lie in computing semantic relations, finding hot concepts and ranking candidate concepts. Semantic similarity between user's input and a candidate keyword is calculated by Relative Information Loss (RIL). Hot keywords are indentified by a new algorithm, which involving clicked time, novelty clicked time, result record number, novelty result record. The rank degree of a keyword is evaluated by its RIL and hot degree. Finally, a software component that takes advantage of DBpedia Ontology, Jena, Ajax and SPARQL in align with these new improvements is developed and deployed on a digital library named iDLib. Better user experience with our new query suggestion software component proves the feasibility and efficiency of the improvement.

show abstract

Comparing Ontologies Using Entropy

Cited by 7 publications

References 2 publications

Engineering ontologies for question answering

Engineering ontologies for question answering

Machine Learning Analysis for Data Incompleteness (MADI): Analyzing the Data Completeness of Patient Records Using a Random Variable Approach to Predict the Incompleteness of Electronic Health Records

Improving Query Suggestion for Digital Libraries

Contact Info

Product

Resources

About