engleski

Robust Keyphrase Extraction For A Large-Scale Croatian News Production System

Summarizing an article with just a few keyphrases can be a difficult task, even for trained experts. Large-scale keyphrase extraction requires a method that is fast and reliable, and yet relatively effective. In this paper we describe such a keyphrase extraction system developed for a large- scale Croatian news production system. We describe how the system works and evaluate the implemented keyphrase extraction methods using a gold set annotated by human annotators. The results indicate that, despite the simplicity of our approach, the performance of the system is comparable to that of the human annotators.

keyword extraction; news production system; information extraction; natural language processing; Croatian language

nije evidentirano