A comparative evaluation of off-the-shelf distributed semantic representations for modelling behavioural data. Issue 3 (18th May 2016)

• Record Type: Journal Article
• Authors: Pereira, Francisco; Gershman, Samuel; Ritter, Samuel; Botvinick, Matthew
• Is Part Of: Cognitive neuropsychology. Volume 33:Issue 3/4(2016)
• Page Start: 175
• Page End: 190
• Publication Date: 2016-05-18
• Subjects: Distributed semantic representation -- evaluation -- semantic space -- semantic vector; Neuropsychology -- Periodicals; 152
• DOI: 10.1080/02643294.2016.1176907
• Languages: English
• ISSNs: 0264-3294

Abstract

ABSTRACT: In this paper we carry out an extensive comparison of many off-the-shelf distributed semantic vectors representations of words, for the purpose of making predictions about behavioural results or human annotations of data. In doing this comparison we also provide a guide for how vector similarity computations can be used to make such predictions, and introduce many resources available both in terms of datasets and of vector representations. Finally, we discuss the shortcomings of this approach and future research directions that might address them.