This paper explores the possibilities of analogical reasoning with vector space models. Given two pairs of words with the same relation (e.g. man:woman :: king:queen), it was proposed that the offset between one pair of the corresponding word vectors can be used to identify the unknown member of the other pair (king-man + woman = ?queen). We argue against such "linguistic regularities" as a model for linguistic relations in vector space models and as a benchmark, and we show that the vector offset (as well as two other, better-performing methods) suffers from dependence on vector similarity.
CITATION STYLE
Rogers, A., Drozd, A., & Li, B. (2017). The (too many) problems of analogical reasoning with word vectors. In *SEM 2017 - 6th Joint Conference on Lexical and Computational Semantics, Proceedings (pp. 135–148). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/s17-1017
Mendeley helps you to discover research relevant for your work.