Title
Evaluating Semantic Metrics On Tasks Of Concept Similarity
Abstract
This study presents an evaluation of WordNet-based semantic similarity and relatedness measures in tasks focused on concept similarity. Assuming similarity as distinct from relatedness, the goal is to fill a gap within the current body of work in the evaluation of similarity and relatedness measures. Past studies have either focused entirely on relatedness or only evaluated judgments over words rather than concepts. In this study, first, concept similarity measures are evaluated over human judgments by using existing sets of word similarity pairs that we annotated with word senses. Next, an application-oriented study is presented by integrating similarity and relatedness measures into an algorithm which relies on concept similarity. Interestingly, the results find metrics categorized as measuring relatedness to be strongest in correlation with human judgments of concept similarity, though the difference in correlation is small. On the other hand, an information content metric, categorized as measuring similarity, is notably strongest according to the application-oriented evaluation. Copyright © 2011, Association for the Advancement of Artificial Intelligence. All rights reserved.
Publication Date
9-9-2011
Publication Title
Proceedings of the 24th International Florida Artificial Intelligence Research Society, FLAIRS - 24
Number of Pages
299-304
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
Copyright Status
Unknown
Socpus ID
80052411240 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/80052411240
STARS Citation
Schwartz, Hansen A. and Gomez, Fernando, "Evaluating Semantic Metrics On Tasks Of Concept Similarity" (2011). Scopus Export 2010-2014. 2848.
https://stars.library.ucf.edu/scopus2010/2848