This paper presents results of a work on crawling CEUR Workshop proceedings web site to a Linked Open Data (LOD) dataset in the framework of ESWC 2014 Semantic Publishing Challenge 2014. Our approach is based on using an extensible template-dependent crawler and DBpedia for linking extracted entities, such as the names of universities and countries.
@article{arxiv.1408.1260,
title = {Unstable markup: A template-based information extraction from web sites with unstable markup},
author = {Maxim Kolchin and Fedor Kozlov},
journal= {arXiv preprint arXiv:1408.1260},
year = {2014}
}