{"pk":27111,"title":"Evaluating vector-space models of analogy","subtitle":null,"abstract":"Vector-space representations provide geometric tools for rea-soning about the similarity of a set of objects and their relation-ships. Recent machine learning methods for deriving vector-space embeddings of words (e.g., word2vec) have achievedconsiderable success in natural language processing. Thesevector spaces have also been shown to exhibit a surprising ca-pacity to capture verbal analogies, with similar results for nat-ural images, giving new life to a classic model of analogies asparallelograms that was first proposed by cognitive scientists.We evaluate the parallelogram model of analogy as applied tomodern word embeddings, providing a detailed analysis of theextent to which this approach captures human relational sim-ilarity judgments in a large benchmark dataset. We find thatthat some semantic relationships are better captured than oth-ers. We then provide evidence for deeper limitations of the par-allelogram model based on the intrinsic geometric constraintsof vector spaces, paralleling classic results for first-order simi-larity.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[{"word":"analogy; word2vec; GloVe; vector space models"}],"section":"Posters: Papers","is_remote":true,"remote_url":"https://escholarship.org/uc/item/7pq7695p","frozenauthors":[{"first_name":"Dawn","middle_name":"","last_name":"Chen","name_suffix":"","institution":"University of California, Berkeley","department":""},{"first_name":"Joshua","middle_name":"C.","last_name":"Peterson","name_suffix":"","institution":"University of California, Berkeley","department":""},{"first_name":"Thomas","middle_name":"L.","last_name":"Griffiths","name_suffix":"","institution":"University of California, Berkeley","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"2017-01-01T18:00:00Z","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/27111/galley/16747/download/"}]}