creators_name: Burns, Brendan creators_name: Sutton, Charles creators_name: Morrison, Clayton creators_name: Cohen, Paul editors_name: Prince, Christopher G. editors_name: Berthouze, Luc editors_name: Kozima, Hideki editors_name: Bullock, Daniel editors_name: Stojanov, Georgi editors_name: Balkenius, Christian type: confpaper datestamp: 2004-02-12 lastmod: 2011-03-11 08:55:25 metadata_visibility: show title: Information Theory and Representation in Associative Word Learning ispublished: pub subjects: comp-sci-mach-learn subjects: comp-sci-art-intel subjects: comp-sci-robot full_text_status: public keywords: associative language learning, information theory, Multi-Stream Dependency Detection, autonomous agent abstract: 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. date: 2003 date_type: published volume: 101 publisher: Lund University Cognitive Studies pagerange: 65-71 refereed: TRUE citation: Burns, Brendan and Sutton, Charles and Morrison, Clayton and Cohen, Paul (2003) Information Theory and Representation in Associative Word Learning. [Conference Paper] document_url: http://cogprints.org/3331/1/Burns.pdf