The Journal of Machine Learning Research
The mathematics of statistical machine translation: parameter estimation
Computational Linguistics - Special issue on using large corpora: II
Early lexical development in a self-organizing neural network
Neural Networks - 2004 Special issue: New developments in self-organizing systems
Affordance based word-to-meaning association
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Learning words and their meanings from unsegmented child-directed speech
HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
EACL '12 Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics
Exploiting social information in grounded language learning via grammatical reductions
ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1
| Hi-index | 0.01 |
Previous studies on early language acquisition have shown that word meanings can be acquired by an associative procedure that maps perceptual experience onto linguistic labels based on cross-situational observation. Recently, a social-pragmatic account focuses on the effect of the child's social-cognitive capacities, such as joint attention and intention reading. This paper argues that statistical and social cues can be seamlessly integrated to facilitate early word learning. To support this idea, we first introduce a statistical learning mechanism that provides a formal account of cross-situational observation. A unified model is then presented that is able to make use of different kinds of embodied social cues, such as joint attention and prosody in maternal speech, in the statistical learning framework. In a computational analysis of infant data, our unified model performs significantly better than the purely statistical approach in computing word-meaning associations.