Analogy perception applied to seven tests of word comprehension

  1. (PDF, 296 KB)
  2. Get@NRC: Analogy perception applied to seven tests of word comprehension (Opens in a new window)
DOIResolve DOI:
AuthorSearch for:
Journal titleJournal of Experimental & Theoretical Artificial Intelligence
Pages343362; # of pages: 20
Subjectanalogies; word comprehension; test-based AI; semantic relations; synonyms; antonyms
AbstractIt has been argued that analogy is the core of cognition. In AI research, algorithms for analogy are often limited by the need for hand-coded high-level representations as input. An alternative approach is to use high-level perception, in which high-level representations are automatically generated from raw data. Analogy perception is the process of recognizing analogies using high-level perception. We present PairClass, an algorithm for analogy perception that recognizes lexical proportional analogies using representations that are automatically generated from a large corpus of raw textual data. A proportional analogy is an analogy of the form A:B::C:D, meaning “A is to B as C is to D”. A lexical proportional analogy is a proportional analogy with words, such as carpenter:wood::mason:stone. PairClass represents the semantic relations between two words using a high-dimensional feature vector, in which the elements are based on frequencies of patterns in the corpus. PairClass recognizes analogies by applying standard supervised machine learning techniques to the feature vectors. We show how seven different tests of word comprehension can be framed as problems of analogy perception and we then apply PairClass to the seven resulting sets of analogy perception problems. We achieve competitive results on all seven tests. This is the first time a uniform approach has handled such a range of tests of word comprehension.
Publication date
AffiliationNRC Institute for Information Technology; National Research Council Canada
Peer reviewedNo
NPARC number18456258
Export citationExport as RIS
Report a correctionReport a correction
Record identifier90710a15-d0a7-4497-8f9f-6d57b9a25cb3
Record created2011-08-18
Record modified2016-05-09
Bookmark and share
  • Share this page with Facebook (Opens in a new window)
  • Share this page with Twitter (Opens in a new window)
  • Share this page with Google+ (Opens in a new window)
  • Share this page with Delicious (Opens in a new window)