Subsymbolic natural language processing: an integrated model of scripts, lexicon, and memory
Subsymbolic natural language processing: an integrated model of scripts, lexicon, and memory
Rich classes inferable from positive data
Information and Computation
Learnable classes of categorial grammars
Learnable classes of categorial grammars
Foundations of Computational Linguistics: Man-Machine Communication in Natural Language
Foundations of Computational Linguistics: Man-Machine Communication in Natural Language
Introduction To Automata Theory, Languages, And Computation
Introduction To Automata Theory, Languages, And Computation
A linguistic investigation into unsupervised DOP
CACLA '07 Proceedings of the Workshop on Cognitive Aspects of Computational Language Acquisition
Hi-index | 0.00 |
The logical problem of language is grounded on arguments from poverty of positive evidence and arguments from poverty of negative evidence. Careful analysis of child language corpora shows that, if one assumes that children learn through item-based constructions, there is an abundance of positive evidence. Arguments regarding the poverty of negative evidence can also be addressed by the mechanism of conservative item-based learning. When conservativism is abandoned, children can rely on competition, cue construction, monitoring and probabilistic identification to derive information from positive data to recover from overgeneralization.