An Evolutionary Approach to Automatically Optimise Web Content Extraction
IIS'09: Proceedings of the 17th International Conference Intelligent Information Systems. Warsaw, Poland. 2009 S. 331 - 343
Erscheinungsjahr: 2009
Publikationstyp: Buchbeitrag (Konferenzbeitrag)
Sprache: Englisch
Inhaltszusammenfassung
Web content extraction is the task of identifying the main content of a web document. In the last years, research has spawned several algorithms to address this task and objective measures to evaluate the performance of such methods. The behaviour of many of these algorithms can be influenced via parameteres, but time consuming evaluation has so far prevented a thorough manual or automatic finetuning and optimisation of the parameter settings. This paper presents an evolutionary...Web content extraction is the task of identifying the main content of a web document. In the last years, research has spawned several algorithms to address this task and objective measures to evaluate the performance of such methods. The behaviour of many of these algorithms can be influenced via parameteres, but time consuming evaluation has so far prevented a thorough manual or automatic finetuning and optimisation of the parameter settings. This paper presents an evolutionary approach as a suitable solution to find good parameter settings.» weiterlesen» einklappen
Klassifikation
DFG Fachgebiet:
Informatik
DDC Sachgruppe:
Informatik
