నైరూప్య

Towards Facts Extraction from Texts in the Polish Language

Tomasz Boiński, Adam Brzeski

The Polish language differs from English in many ways. It has more complicated conjugation and declination. Because of that automatic facts extraction from texts is difficult. In this paper we present basic differences between those languages. The paper presents an algorithm for extraction of facts from articles from Polish Wikipedia. The algorithm is based on 7 proposed facts schemes that are searched for in the analyzed text. The analysis includes morphosyntactic tagging, named entity extraction and relation identification. The results acquired for an exemplary Wikipedia text is presented. We indicate the free word formation principle as the main difficulty in the Polish texts analysis. At the same time satisfactory performance of the tagging and analysis tools for the Polish language was confirmed in the conducted experiment.