Extraction of Lexico-Syntactic Information and Acquisition of Causality Schemas for Text Annotation

We present the INSYSE method for the annotation of texts, based on extraction of semantic relations from syntactic structures. We apply this method to a corpus of 5000 Medline abstracts about central nervous system diseases and gene interactions. Our cooperative approach focuses on (1) extracting lexico-syntactic information from sentences in the corpus comprising causation lexemes and (2) elaborating unification grammar rules which enable to extract instantiated conceptual schemas from this information. They are translated into RDF annotations which used by the semantic search engine Corese to query the corpus about functions of genes and their correlations with particular diseases.