Publications

Methods and resources for computing semantic relatedness

Yue Feng and Ebrahim Bagheri
Reference:
Links to Publication: [doi][www][pdf]
Abstract:
Semantic relatedness (SR) is defined as a measurement that quantitatively identifies some form of lexical or functional association between two words or concepts based on the contextual or semantic similarity of those two words regardless of their syntactical differences. Section 1 of the entry outlines the working definition of SR and its applications and challenges. Section 2 identifies the knowledge resources that are popular among SR methods. Section 3 reviews the primary measurements used to calculate SR. Section 4 reviews the evaluation methodology which includes gold standard dataset and methods. Finally, Sec. 5 introduces further reading. In order to develop appropriate SR methods, there are three key aspects that need to be examined: (1) the knowledge resources that are used as the source for extracting SR; (2) the methods that are used to quantify SR based on the adopted knowledge resource; and (3) the datasets and methods that are used for evaluating SR techniques. The first aspect involves the selection of knowledge bases such as WordNet or Wikipedia. Each knowledge base has its merits and downsides which can directly affect the accuracy and the coverage of the SR method. The second aspect relies on different methods for utilizing the beforehand selected knowledge resources, for example, methods that depend on the path between two words, or a vector representation of the word. As for the third aspect, the evaluation for SR methods consists of two aspects, namely (1) the datasets that are used and (2) the various performance measurement methods. SR measures are increasingly applied in information retrieval to provide semantics between query and documents to reveal relatedness between non-syntactically-related content. Researchers have already applied many different information and knowledge sources in order to compute SR between two words. Empirical research has already shown that results of many of these SR techniques have reasonable correlation with human subjects interpretation of relatedness between two words.
Bibtex Entry:
@incollection{escri/FengB17, author = {Yue Feng and Ebrahim Bagheri }, title = {Methods and resources for computing semantic relatedness}, booktitle = {Encyclopedia with Semantic Computing and Robotic Intelligence}, volume = {01}, number = {01}, pages = {1630005 [5]}, year = {2017}, url = {http://www.worldscientific.com/doi/abs/10.1142/S2425038416300056}, doi = {10.1142/S2425038416300056}, webpdf = {http://ls3.rnet.ryerson.ca/papers/Methods_and_resources_for_computing_semantic_relatedness-escri2017.pdf}, abstract = {Semantic relatedness (SR) is defined as a measurement that quantitatively identifies some form of lexical or functional association between two words or concepts based on the contextual or semantic similarity of those two words regardless of their syntactical differences. Section 1 of the entry outlines the working definition of SR and its applications and challenges. Section 2 identifies the knowledge resources that are popular among SR methods. Section 3 reviews the primary measurements used to calculate SR. Section 4 reviews the evaluation methodology which includes gold standard dataset and methods. Finally, Sec. 5 introduces further reading. In order to develop appropriate SR methods, there are three key aspects that need to be examined: (1) the knowledge resources that are used as the source for extracting SR; (2) the methods that are used to quantify SR based on the adopted knowledge resource; and (3) the datasets and methods that are used for evaluating SR techniques. The first aspect involves the selection of knowledge bases such as WordNet or Wikipedia. Each knowledge base has its merits and downsides which can directly affect the accuracy and the coverage of the SR method. The second aspect relies on different methods for utilizing the beforehand selected knowledge resources, for example, methods that depend on the path between two words, or a vector representation of the word. As for the third aspect, the evaluation for SR methods consists of two aspects, namely (1) the datasets that are used and (2) the various performance measurement methods. SR measures are increasingly applied in information retrieval to provide semantics between query and documents to reveal relatedness between non-syntactically-related content. Researchers have already applied many different information and knowledge sources in order to compute SR between two words. Empirical research has already shown that results of many of these SR techniques have reasonable correlation with human subjects interpretation of relatedness between two words.} }




Powered by WordPress