Knowledge of language and principles of naturalistic learning are rarely used in information extraction systems. The main challenge for these systems is to provide conceptually relevant information while minimizing computational costs. This paper argues that knowledge of language and principles of naturalistic learning may enhance the capacity of intelligent systems to process linguistic expressions and simulate humans' capacity for language. We contrast humans' genetic endowment to genetic programming, as well as naturalistic learning to Reinforcement Learning used to extract information form texts. We point to limits of machine learning methodology and we draw consequences for knowledge science.
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
Tel.: +1 703 830 6300
Fax: +1 703 830 2300 firstname.lastname@example.org
(Corporate matters and books only) IOS Press c/o Accucoms US, Inc.
For North America Sales and Customer Service
West Point Commons
Lansdale PA 19446
Tel.: +1 866 855 8967
Fax: +1 215 660 5042 email@example.com