GPKEX: Genetically Programmed Keyphrase Extraction from Croatian Texts
Marko Bekavac, Jan Šnajder · 2013
We describe GPKEX, a keyphrase extraction method based on genetic programming. We represent keyphrase scoring measures as syntax trees and evolve them to produce rankings for keyphrase candidates extracted from text. We apply and evaluate GPKEX on Croatian newspaper articles. We show that GPKEX can evolve simple and interpretable keyphrase scoring measures that perform comparably to more complex machine learning methods previously developed for Croatian. 1