Evolutionary learning of meta-rules for text classification

Juan-Carlos Gomez, Stijn Hoskens, Marie-Francine MoensGECCO (Companion) 2017 · OpenReview

Abstract

This paper presents an evolutionary method for learning lists of meta-rules for generalizing the selection of the best classifier for a given text dataset. The method builds rules based on features of a set of training text datasets, and evolves them using special crossover and mutation operators. Once the rules are learned, they are tested in a different set of datasets to demonstrate their accuracy and generality. Our experiments show encouraging results.
BibTeX
@inproceedings{gomez2017evolutionary,
  author = {Juan-Carlos Gomez and Stijn Hoskens and Marie-Francine Moens},
  title = {{Evolutionary learning of meta-rules for text classification}},
  booktitle = {GECCO (Companion)},
  year = {2017},
  url = {https://openreview.net/forum?id=GjL53M_Qtii},
}

Loading related content...

Figure