A Compositional and Interpretable Semantic Space
Full Text: N15-1004.pdf
Vector Space Models (VSMs) of Semantics are useful tools for exploring the semantics of single words, and the composition of words to make phrasal meaning. While many methods can estimate the meaning (i.e. vector) of a phrase, few do so in an interpretable way. We introduce a new method (CNNSE) that allows word and phrase vectors to adapt to the notion of composition. Our method learns a VSM that is both tailored to support a chosen semantic composition operation, and whose resulting features have an intuitive interpretation. Interpretability allows for the exploration of phrasal semantics, which we leverage to analyze performance on a behavioral task.
Citation
A. Fyshe, L. Wehbe, P. Talukdar, B. Murphy, T. Mitchell. "A Compositional and Interpretable Semantic Space". NAACL Annual Conference of the North American Chapter of the Association for Computational Linguisti, pp 32–41, May 2015.| Keywords: | |
| Category: | In Conference |
| Web Links: | DOI: |
| ACL |
BibTeX
@incollection{Fyshe+al:NAACL15,
author = {Alona Fyshe and Leila Wehbe and Partha Talukdar and Brian Murphy
and Tom M. Mitchell},
title = {A Compositional and Interpretable Semantic Space},
Pages = {32–41},
booktitle = {NAACL Annual Conference of the North American Chapter of the
Association for Computational Linguisti},
year = 2015,
}Last Updated: June 22, 2020Submitted by Sabina P
