Ontology Population and Alignment for the Legal Domain: YAGO, Wikipedia and LKIF

We present a methodology and framework to align ontologies through annotation of texts, and we show how this methodology applies successfully to the legal domain. This method reduces the difficulty of aligning ontologies, because annotators are asked to associate two labels from different inventories to a concrete example, which requires a simple judgment. In a second phase, those correspondences are consolidated into a proper alignment. The resulting alignment is a partial connection between diverse ontologies. By annotating judgments of the European Court of Human Rights, we have aligned an ontology of the legal domain, LKIF, to YAGO, we have thus populated LKIF in order to train a legal Named Entity Recognizer and Classifier with examples from the Wikipedia that are trivially mapped to LKIF classes. The resulting resources and the best practices we defined supported a step towards automation in legal informatics.