ISA meets Lara: an incremental word space model for cognitively plausible simulations of semantic learning

Authors:
Marco Baroni;Alessandro Lenci;Luca Onnis
Affiliations:
CIMeC (University of Trento), Rovereto, Italy;University of Pisa, Pisa, Italy;Cornell University, Ithaca, NY
Venue:
CACLA '07 Proceedings of the Workshop on Cognitive Aspects of Computational Language Acquisition
Year:
2007

Citing 2
Cited 3

Foundations of statistical natural language processing

Foundations of statistical natural language processing
Early lexical development in a self-organizing neural network

Neural Networks - 2004 Special issue: New developments in self-organizing systems

The S-Space package: an open source package for word space models

ACLDemos '10 Proceedings of the ACL 2010 System Demonstrations
The automatic identification of lexical variation between language varieties

Natural Language Engineering
Modeling coherence in ESOL learner texts

Proceedings of the Seventh Workshop on Building Educational Applications Using NLP

Quantified Score

Hi-index	0.00

Visualization

Abstract

We introduce Incremental Semantic Analysis, a fully incremental word space model, and we test it on longitudinal child-directed speech data. On this task, ISA outperforms the related Random Indexing algorithm, as well as a SVD-based technique. In addition, the model has interesting properties that might also be characteristic of the semantic space of children.