This site has been permanently archived. This is a static copy provided by the University of Southampton.
TY - GEN N1 - NRC-50738 ID - cogprints6305 UR - http://cogprints.org/6305/ A1 - Turney, Peter D. Y1 - 2008/12/22/ N2 - Many AI researchers and cognitive scientists have argued that analogy is the core of cognition. The most influential work on computational modeling of analogy-making is Structure Mapping Theory (SMT) and its implementation in the Structure Mapping Engine (SME). A limitation of SME is the requirement for complex hand-coded representations. We introduce the Latent Relation Mapping Engine (LRME), which combines ideas from SME and Latent Relational Analysis (LRA) in order to remove the requirement for hand-coded representations. LRME builds analogical mappings between lists of words, using a large corpus of raw text to automatically discover the semantic relations among the words. We evaluate LRME on a set of twenty analogical mapping problems, ten based on scientific analogies and ten based on common metaphors. LRME achieves human-level performance on the twenty problems. We compare LRME with a variety of alternative approaches and find that they are not able to reach the same level of performance. PB - AI Access Foundation KW - analogy KW - metaphor KW - semantic relations KW - structure mapping KW - vector space models KW - analogical mapping KW - latent relational analysis TI - The Latent Relation Mapping Engine: Algorithm and Experiments SP - 615 AV - public EP - 655 ER -