%A Brendan Burns
%A Charles Sutton
%A Clayton Morrison
%A Paul Cohen
%T Information Theory and Representation in Associative Word Learning
%X A significant portion of early language learning
can be viewed as an associative learning
problem. We investigate the use of associative
language learning based on the principle that
words convey Shannon information about the
environment. We discuss the shortcomings
in representation used by previous associative
word learners and propose a functional representation
that not only denotes environmental
categories, but serves as the basis for activities
and interaction with the environment.
We present experimental results with an autonomous
agent acquiring language.
%K associative language learning, information theory, Multi-Stream Dependency Detection, autonomous agent
%P 65-71
%E Christopher G. Prince
%E Luc Berthouze
%E Hideki Kozima
%E Daniel Bullock
%E Georgi Stojanov
%E Christian Balkenius
%V 101
%D 2003
%I Lund University Cognitive Studies
%L cogprints3331

<script src="//archive-bar.soton.ac.uk/archive-bar.js"></script>