11th Annual Conference of the International Speech Communication Association

Makuhari, Chiba, Japan
September 26-30. 2010

Active Word Learning Under Uncertain Input Conditions

Maarten Versteegh (1), Louis ten Bosch (2), Lou Boves (2)

(1) IMPRS for Language Sciences, The Netherlands
(2) Radboud Universiteit Nijmegen, The Netherlands

In this paper we investigate a computational model of word learning that is cognitively plausible. The model is partly trained on incorrect form-referent pairings, modelling the input to a word-learning child that may contain such mismatches due to inattention to a joint communicative scene. We introduce a procedure of active learning, based on attested cognitive processes. We then show how this procedure can help overcome the unreliability of the input by detecting and correcting the mismatches by reliance on previously built up experience.

Full Paper

Bibliographic reference.  Versteegh, Maarten / Bosch, Louis ten / Boves, Lou (2010): "Active word learning under uncertain input conditions", In INTERSPEECH-2010, 2930-2933.