Challenges as enablers for high quality Linked Data: insights from the Semantic Publishing Challenge

摘要: While most challenges organized so far in the Semantic Web domain are focused on comparing tools with respect to different criteria such as their features and competencies, or exploiting semantically enriched data, Evaluation Challenges series, co-located ESWC Conference, aims compare them based output, namely produced dataset. The Publishing Challenge is one of these challenges. Its goal involve participants extracting data from heterogeneous sources scholarly publications, producing Linked Data that can be exploited by community itself. This paper reviews lessons learned both (i) overall organization Challenge, regarding definition tasks, building input dataset forming evaluation, (ii) results participants, proposed approaches, used tools, preferred vocabularies three editions 2014, 2015 2016. We compared other In this paper, we distill best practices for organizing could applied similar events, report observations publishing derived submitted solutions. conclude higher quality may achieved when a result challenge, because competition becomes an incentive, while solutions become better they evaluated against rules challenge.