Taxonomies by the numbers

Gates, Stephen C.; Teiken, Wilfried; Cheng, Keh-Shin F.

doi:10.1145/1099554.1099703

Cited by 27 publications

(4 citation statements)

References 21 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Proposed solution uses the cosine similarity function [19] to check the similarity between the extracted concepts representing two documents. The cosine similarity function is shown in

\begin{matrix} T1 \\ s i m (s, d) = \frac{\sum_{t \in ((), s, d)} w_{s} (t) \cdot w_{d} (t)}{\sqrt{{false\sum}_{t \in s} w_{s} {(|, t)}^{normal2}} \cdot \sqrt{{false\sum}_{t \in s} w_{d} {(|, t)}^{normal2}}}, \end{matrix}

where s , d are the two documents, w s ( t ) is the weight of term t in the s document, and w d ( t ) is the weight of term t in the d document.…”

Section: Overall Architecture Of the Proposed Methodologymentioning

confidence: 99%

Semantic Clustering of Search Engine Results

Soliman

Elsayed

Hassan

2015

The Scientific World Journal

View full text Add to dashboard Cite

This paper presents a novel approach for search engine results clustering that relies on the semantics of the retrieved documents rather than the terms in those documents. The proposed approach takes into consideration both lexical and semantics similarities among documents and applies activation spreading technique in order to generate semantically meaningful clusters. This approach allows documents that are semantically similar to be clustered together rather than clustering documents based on similar terms. A prototype is implemented and several experiments are conducted to test the prospered solution. The result of the experiment confirmed that the proposed solution achieves remarkable results in terms of precision.

show abstract

“…Proposed solution uses the cosine similarity function [19] to check the similarity between the extracted concepts representing two documents. The cosine similarity function is shown in

\begin{matrix} T1 \\ s i m (s, d) = \frac{\sum_{t \in ((), s, d)} w_{s} (t) \cdot w_{d} (t)}{\sqrt{{false\sum}_{t \in s} w_{s} {(|, t)}^{normal2}} \cdot \sqrt{{false\sum}_{t \in s} w_{d} {(|, t)}^{normal2}}}, \end{matrix}

where s , d are the two documents, w s ( t ) is the weight of term t in the s document, and w d ( t ) is the weight of term t in the d document.…”

Section: Overall Architecture Of the Proposed Methodologymentioning

confidence: 99%

Semantic Clustering of Search Engine Results

Soliman

Elsayed

Hassan

2015

The Scientific World Journal

View full text Add to dashboard Cite

show abstract

“…Several works address taxonomy construction by exploiting well-known data mining techniques. Mostly proposed algorithms exploited clustering techniques to provide a well-founded structuring of concepts of interest (Dhillon & Modha, 2001;Clifton et al, 2004;Gates, Teiken, & Cheng, 2005;Ienco & Meo, 2008). The mostly used techniques are based on hierarchical clustering, which produces a set of nested clusters organized as a hierarchical tree, called dendrogram.…”

Section: Previous Workmentioning

confidence: 99%

“…The mostly used techniques are based on hierarchical clustering, which produces a set of nested clusters organized as a hierarchical tree, called dendrogram. The most relevant application context in which clustering techniques have been adopted to address taxonomy construction is the context of textual data analysis (Dhillon & Modha, 2001;Clifton et al, 2004;Gates et al, 2005;Ienco & Meo, 2008;Hofmann, 1999;Hatzivassiloglou, Gravano, & Maganti, 2000). However, the focus of our approach is different from the aforementioned one.…”

Section: Previous Workmentioning

confidence: 99%

Semi-Automatic Ontology Construction by Exploiting Functional Dependencies and Association Rules

Cerquitelli

Cagliero

Garza

2011

International Journal on Semantic Web and Information Systems

View full text Add to dashboard Cite

This paper presents a novel semi-automatic approach to construct conceptual ontologies over structured data by exploiting both the schema and content of the input dataset. It effectively combines two well-founded database and data mining techniques, i.e., functional dependency discovery and association rule mining, to support domain experts in the construction of meaningful ontologies, tailored to the analyzed data, by using Description Logic (DL). To this aim, functional dependencies are first discovered to highlight valuable conceptual relationships among attributes of the data schema (i.e., among concepts). The set of discovered correlations effectively support analysts in the assertion of the Tbox ontological statements (i.e., the statements involving shared data conceptualizations and their relationships). Then, the analyst-validated dependencies are exploited to drive the association rule mining process. Association rules represent relevant and hidden correlations among data content and they are used to provide valuable knowledge at the instance level. The pushing of functional dependency constraints into the rule mining process allows analysts to look into and exploit only the most significant data item recurrences in the assertion of the Abox ontological statements (i.e., the statements involving concept instances and their relationships)

show abstract

“…Kiritchenko et al [32] dealt with hierarchical categorization, and introduced the notion of consistent classification. Gates and Teiken [20] described a system for the construction of taxonomies which yielded high accuracy for automated categorization systems. Dekel et al [15] formulated the hierarchical classification task as an optimization problem with varying margin constraints, and described new online and batch algorithms for solving it.…”

Section: Text Classification or Categorizationmentioning

confidence: 99%

Organization is sharing

Senra¹

View full text Add to dashboard Cite

Information sharing has always been a key issue in any kind of joint effort. Paradoxically, with the data deluge, the more information available, the harder it is to design and implement solutions that effectively foster such sharing. This thesis analyzes distinct aspects of sharing -from eScience-related environments to personal information. As a result of this analysis, it provides answers to some of the problems encountered, along three axes.The first, SciFrame, is a specific framework that describes systems or processes involving scientific digital data manipulation, serving as a descriptive pattern to help system comparison. The adoption of SciFrame to describe distinct scientific virtual environments allows identifying commonalities and points for interoperation.The second axe contribution addresses the specific problem of communication between arbitrary systems and services provided by distinct database platforms, via the use of the so-called database descriptors or DBDs. These descriptors contribute to provide independence between applications and the services, thereby enhancing sharing across applications and databases.The third contribution, Organographs, provides means to deal with multifaceted information organization. It addresses problems of sharing personal information by means of exploiting the way we organize such information. Here, rather than trying to provide means to share the information itself, the unit of sharing is the organization of the information. By designing and sharing organographs, distinct groups provide each other dynamic, reconfigurable views of how information is organized, thereby promoting interoperability and reuse. Organographs are an innovative approach to hierarchical data management.These three contributions are centered on the basic idea of building and sharing hierarchical organizations. Part of these contributions was validated by case studies and, in the case of organographs, an actual implementation.

show abstract

Taxonomies by the numbers

Cited by 27 publications

References 21 publications

Semantic Clustering of Search Engine Results

Semantic Clustering of Search Engine Results

Semi-Automatic Ontology Construction by Exploiting Functional Dependencies and Association Rules

Organization is sharing

Contact Info

Product

Resources

About