DEBORA: Dependency-Based Method for Extracting Entity-Relationship Triples from Open-Domain Texts in Polish

摘要

This paper describes DEBORA - a dependency-based approach to the extraction of relations between named entities from Polish open-domain texts. The presented method designed for the purpose of the conducted experiment is adapted to morpho-syntactic properties of Polish. Results show that the method is applicable for Polish, even if there is a room for improvement. The extraction approach may be applied to the problem of graphical entity summarisation.