A Parallel Approach to Modeling Language Learning and Understanding in Young Children

May 2000

Proceedings of the Thirteenth International Florida Artificial Intelligence Research Society Conference (FLAIRS 2000)

Volume

Proceedings of the Thirteenth International Florida Artificial Intelligence Research Society Conference (FLAIRS 2000)

All Papers

To reduce the complexity of studying a parallel mechanism for natural language learning and understanding which supports both utterance and discourse processing, we propose a computational model demonstrating the performance of a young language user just starting to construct two and three word utterances. Our model attempts to capture the explanatory aspects of parallel language processing and the division between long and short term memory which have been shown as important factors in human language learning and performance. We also address the pragmatic consideration of building and supporting the resulting parallel system on a cluster of SMP computers.