<> "The repository administrator has not yet configured an RDF license."^^ . <> . . "Similarity of Semantic Relations"^^ . "There are at least two kinds of similarity. Relational similarity is \ncorrespondence between relations, in contrast with attributional similarity, \nwhich is correspondence between attributes. When two words have a high \ndegree of attributional similarity, we call them synonyms. When two pairs \nof words have a high degree of relational similarity, we say that their \nrelations are analogous. For example, the word pair mason:stone is analogous \nto the pair carpenter:wood. This paper introduces Latent Relational Analysis (LRA), \na method for measuring relational similarity. LRA has potential applications in many \nareas, including information extraction, word sense disambiguation, \nand information retrieval. Recently the Vector Space Model (VSM) of information \nretrieval has been adapted to measuring relational similarity, \nachieving a score of 47% on a collection of 374 college-level multiple-choice \nword analogy questions. In the VSM approach, the relation between a pair of words is \ncharacterized by a vector of frequencies of predefined patterns in a large corpus. \nLRA extends the VSM approach in three ways: (1) the patterns are derived automatically \nfrom the corpus, (2) the Singular Value Decomposition (SVD) is used to smooth the frequency \ndata, and (3) automatically generated synonyms are used to explore variations of the \nword pairs. LRA achieves 56% on the 374 analogy questions, statistically equivalent to the \naverage human score of 57%. On the related problem of classifying semantic relations, LRA \nachieves similar gains over the VSM. "^^ . "2006" . . "32" . "3" . . "Computational Linguistics"^^ . . . . . . . . "Peter D."^^ . "Turney"^^ . "Peter D. Turney"^^ . . . . . . "Similarity of Semantic Relations (PDF)"^^ . . . . . . . . . "NRC-48775.pdf"^^ . . . "Similarity of Semantic Relations (Image (PNG))"^^ . . . . . . "preview.png"^^ . . . "Similarity of Semantic Relations (Indexer Terms)"^^ . . . . . . "indexcodes.txt"^^ . . "HTML Summary of #5098 \n\nSimilarity of Semantic Relations\n\n" . "text/html" . . . "Language" . . . "Computational Linguistics" . . . "Semantics" . . . "Machine Learning" . . . "Artificial Intelligence" . .