Títol:
|
Grounded models of semantic representation
|
Autor/a:
|
Silberer, Carina; Lapata, Mirella
|
Abstract:
|
Comunicació presentada a: The 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, celebrada del 12 al 14 de juliol de 2012 a Jeju Island, Corea del Sud. |
Abstract:
|
A popular tradition of studying semantic representation
has been driven by the assumption
that word meaning can be learned from
the linguistic environment, despite ample evidence
suggesting that language is grounded
in perception and action. In this paper we
present a comparative study of models that
represent word meaning based on linguistic
and perceptual data. Linguistic information is
approximated by naturally occurring corpora
and sensorimotor experience by feature norms
(i.e., attributes native speakers consider important
in describing the meaning of a word). The
models differ in terms of the mechanisms by
which they integrate the two modalities. Experimental
results show that a closer correspondence
to human data can be obtained by
uncovering latent information shared among
the textual and perceptual modalities rather
than arriving at semantic knowledge by concatenating
the two. |
Abstract:
|
We acknowledge the support of EPSRC through project grant EP/I032916/1. |
Drets:
|
© ACL, Creative Commons Attribution 3.0 License
|
Tipus de document:
|
Objecte de conferència Article - Versió publicada |
Publicat per:
|
ACL (Association for Computational Linguistics)
|
Compartir:
|
|