Other formats:
BibTeX
LaTeX
RIS
@inproceedings{490363, author = {Žižka, Jan and Šrédl, Michal and Bourek, Aleš}, address = {Berlin Heidelberg New York}, booktitle = {Computional Linguistics and Intelligent Text Processing}, keywords = {machine learning; text document processing; genetic algorithms; naive Bayes method}, language = {eng}, location = {Berlin Heidelberg New York}, isbn = {3-540-00532-3}, pages = {584-587}, publisher = {Springer Verlag}, title = {Searching for Significant Word Associations in Text Documents Using Genetic Algorithms}, year = {2003} }
TY - JOUR ID - 490363 AU - Žižka, Jan - Šrédl, Michal - Bourek, Aleš PY - 2003 TI - Searching for Significant Word Associations in Text Documents Using Genetic Algorithms PB - Springer Verlag CY - Berlin Heidelberg New York SN - 3540005323 KW - machine learning KW - text document processing KW - genetic algorithms KW - naive Bayes method N2 - The paper describes experiments that used Genetic Algorithms for looking for important word assocoations (phrases) in unstructured text documents obtained from the Internet in the area of a specialized medicine branch. Genetic alforithms can evolve sets of word associations with assigned significance weights from the document categorization point of view (relevant and irrelevant documents). The categorization is similarly reliable like the naive Bayes classification based on individual words. In addition, genetic algorithms provided phrases consisting of one, two, and three words. The phrases were quite meaningful from the human point of view. ER -
ŽIŽKA, Jan, Michal ŠRÉDL and Aleš BOUREK. Searching for Significant Word Associations in Text Documents Using Genetic Algorithms. In \textit{Computional Linguistics and Intelligent Text Processing}. Berlin Heidelberg New York: Springer Verlag, 2003, p.~584-587. ISBN~3-540-00532-3.
|