Interpretable Semantic Vectors from a Joint Model of Brain- and Text- Based Meaning
Full Text: P14-1046.pdf
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.
Citation
A. Fyshe, P. Talukdar, B. Murphy, T. Mitchell. "Interpretable Semantic Vectors from a Joint Model of Brain- and Text- Based Meaning". Annual Meeting of the Association for Computational Linguistics (ACL), Baltimore, USA, pp 489–499, June 2014.| Keywords: | |
| Category: | In Conference |
| Web Links: | DOI: |
| ACL |
BibTeX
@incollection{Fyshe+al:14,
author = {Alona Fyshe and Partha Talukdar and Brian Murphy and Tom M.
Mitchell},
title = {Interpretable Semantic Vectors from a Joint Model of Brain- and
Text- Based Meaning},
Pages = {489–499},
booktitle = {Annual Meeting of the Association for Computational Linguistics
(ACL)},
year = 2014,
}Last Updated: June 22, 2020Submitted by Sabina P
