This paper introduces Latent Relational Analysis (LRA), a method for
measuring semantic similarity. LRA measures similarity in the semantic
relations between two pairs of words. When two pairs have a high degree of
relational similarity, they are analogous. For example, the pair cat:meow is
analogous to the pair dog:bark. There is evidence from cognitive science that
relational similarity is fundamental to many cognitive and linguistic tasks
(e.g., analogical reasoning). In the Vector Space Model (VSM) approach to
measuring relational similarity, the similarity between two pairs is calculated
by the cosine of the angle between the vectors that represent the two pairs.
The elements in the vectors are based on the frequencies of manually
constructed patterns in a large corpus. LRA extends the VSM approach in three
ways: (1) patterns are derived automatically from the corpus, (2) Singular
Value Decomposition is used to smooth the frequency data, and (3) synonyms are
used to reformulate word pairs. This paper describes the LRA algorithm and
experimentally compares LRA to VSM on two tasks, answering college-level
multiple-choice word analogy questions and classifying semantic relations in
noun-modifier expressions. LRA achieves state-of-the-art results, reaching
human-level performance on the analogy questions and significantly exceeding
VSM performance on both tasks.
%0 Generic
%1 citeulike:278801
%A Turney, Peter D.
%D 2005
%K ijcai, lra, semantic, similarity
%T Measuring Semantic Similarity by Latent Relational Analysis
%U http://arxiv.org/abs/cs/0508053
%X This paper introduces Latent Relational Analysis (LRA), a method for
measuring semantic similarity. LRA measures similarity in the semantic
relations between two pairs of words. When two pairs have a high degree of
relational similarity, they are analogous. For example, the pair cat:meow is
analogous to the pair dog:bark. There is evidence from cognitive science that
relational similarity is fundamental to many cognitive and linguistic tasks
(e.g., analogical reasoning). In the Vector Space Model (VSM) approach to
measuring relational similarity, the similarity between two pairs is calculated
by the cosine of the angle between the vectors that represent the two pairs.
The elements in the vectors are based on the frequencies of manually
constructed patterns in a large corpus. LRA extends the VSM approach in three
ways: (1) patterns are derived automatically from the corpus, (2) Singular
Value Decomposition is used to smooth the frequency data, and (3) synonyms are
used to reformulate word pairs. This paper describes the LRA algorithm and
experimentally compares LRA to VSM on two tasks, answering college-level
multiple-choice word analogy questions and classifying semantic relations in
noun-modifier expressions. LRA achieves state-of-the-art results, reaching
human-level performance on the analogy questions and significantly exceeding
VSM performance on both tasks.
@electronic{citeulike:278801,
abstract = {{This paper introduces Latent Relational Analysis (LRA), a method for
measuring semantic similarity. LRA measures similarity in the semantic
relations between two pairs of words. When two pairs have a high degree of
relational similarity, they are analogous. For example, the pair cat:meow is
analogous to the pair dog:bark. There is evidence from cognitive science that
relational similarity is fundamental to many cognitive and linguistic tasks
(e.g., analogical reasoning). In the Vector Space Model (VSM) approach to
measuring relational similarity, the similarity between two pairs is calculated
by the cosine of the angle between the vectors that represent the two pairs.
The elements in the vectors are based on the frequencies of manually
constructed patterns in a large corpus. LRA extends the VSM approach in three
ways: (1) patterns are derived automatically from the corpus, (2) Singular
Value Decomposition is used to smooth the frequency data, and (3) synonyms are
used to reformulate word pairs. This paper describes the LRA algorithm and
experimentally compares LRA to VSM on two tasks, answering college-level
multiple-choice word analogy questions and classifying semantic relations in
noun-modifier expressions. LRA achieves state-of-the-art results, reaching
human-level performance on the analogy questions and significantly exceeding
VSM performance on both tasks.}},
added-at = {2010-12-17T18:47:41.000+0100},
archiveprefix = {arXiv},
author = {Turney, Peter D.},
biburl = {https://www.bibsonomy.org/bibtex/2fc4449dfa49942d64719909d3069004b/mortimer_m8},
citeulike-article-id = {278801},
citeulike-linkout-0 = {http://arxiv.org/abs/cs/0508053},
citeulike-linkout-1 = {http://arxiv.org/pdf/cs/0508053},
day = 10,
eprint = {cs/0508053},
interhash = {3c0567df63c65bab066660aed6187a31},
intrahash = {fc4449dfa49942d64719909d3069004b},
keywords = {ijcai, lra, semantic, similarity},
month = Aug,
posted-at = {2005-08-11 14:15:10},
priority = {0},
timestamp = {2010-12-20T11:11:25.000+0100},
title = {{Measuring Semantic Similarity by Latent Relational Analysis}},
url = {http://arxiv.org/abs/cs/0508053},
year = 2005
}