ACM Computing Surveys (CSUR)
Machine learning in automated text categorization
ACM Computing Surveys (CSUR)
Ontology Learning for the Semantic Web
IEEE Intelligent Systems
On the quality of ART1 text clustering
Neural Networks - 2003 Special issue: Advances in neural networks research IJCNN'03
The Journal of Machine Learning Research
Text Mining Handbook: Advanced Approaches in Analyzing Unstructured Data
Text Mining Handbook: Advanced Approaches in Analyzing Unstructured Data
Semiotic Dynamics for Embodied Agents
IEEE Intelligent Systems
Soft Computing - A Fusion of Foundations, Methodologies and Applications - Special issue on neural networks for pattern recognition and data mining
Learning to link with wikipedia
Proceedings of the 17th ACM conference on Information and knowledge management
Web page classification: Features and algorithms
ACM Computing Surveys (CSUR)
The state of the art in tag ontologies: a semantic model for tagging and folksonomies
DCMI '08 Proceedings of the 2008 International Conference on Dublin Core and Metadata Applications
Software Engineering: A Practitioner's Approach
Software Engineering: A Practitioner's Approach
Populating the Semantic Web by Macro-reading Internet Text
ISWC '09 Proceedings of the 8th International Semantic Web Conference
Broad-coverage parsing using human-like memory constraints
Computational Linguistics
Fifty years of AI: from symbols to embodiment - and back
50 years of artificial intelligence
Autonomous and adaptive identification of topics in unstructured text
KES'11 Proceedings of the 15th international conference on Knowledge-based and intelligent information and engineering systems - Volume Part II
A layered reference model of the brain (LRMB)
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Perspectives on Cognitive Informatics and Cognitive Computing
International Journal of Cognitive Informatics and Natural Intelligence
International Journal of Cognitive Informatics and Natural Intelligence
Hi-index | 0.00 |
The author argues that the cognitive processes underlying language understanding may not be logico-deductive or inductive, at least not for basic forms of understanding such as the ability to determine the topics of a text document. To demonstrate this point, they present a human cognition inspired framework for core language understanding and its computational implementation. The framework exploits word related knowledge stored in Long Term Memory LTM as well as Short Term Memory STM limited capacity, neuromorphic spreading activation and neural activation decay to derive the topics of text. The computational model implementing the framework shows the potential of the approach by establishing that the topics generated by the model are as good as those generated by humans.