Interpretable semantic vectors from a joint model of brain-and text-based meaning

Alona Fyshe, Partha P Talukdar, Brian Murphy, Tom M Mitchell

Research output: Chapter in Book/Report/Conference proceedingConference contribution

29 Citations (Scopus)

Abstract

Vector space models (VSMs) represent word meanings as points in a high dimensional space. VSMs are typically created using a large text corpora, and so represent word semantics as observed in text. We present a new algorithm (JNNSE) that can incorporate a measure of semantics not previously used to create VSMs: brain activation data recorded while people read words. The resulting model takes advantage of the complementary strengths and weaknesses of corpus and brain activation data to give a more complete representation of semantics. Evaluations show that the model 1) matches a behavioral measure of semantics more closely, 2) can be used to predict corpus data for unseen words and 3) has predictive power that generalizes across brain imaging technologies and across subjects. We believe that the model is thus a more faithful representation of mental vocabularies.
Original languageEnglish
Title of host publicationThe 52nd Annual Meeting of the Association for Computational Linguistics: Proceedings of the conference volume 1: Long papers
Place of PublicationStroudsburg
PublisherThe Association for Computational Linguistics
Pages489-499
Number of pages11
Volume1
ISBN (Electronic) 9781937284725
Publication statusPublished - Jun 2014
EventThe 52nd Annual Meeting of the Association for Computational Linguistics - Baltimore, United States
Duration: 22 Jun 201427 Jun 2014

Conference

ConferenceThe 52nd Annual Meeting of the Association for Computational Linguistics
CountryUnited States
CityBaltimore
Period22/06/201427/06/2014

Fingerprint Dive into the research topics of 'Interpretable semantic vectors from a joint model of brain-and text-based meaning'. Together they form a unique fingerprint.

Cite this