Chomsky Was (Almost) Right: Ontology-Based Parsing of Texts of a Narrow Domain

The common approach to the analysis of natural texts implies that semantic analysis should following the stage of parsing. However, medical texts are known as very complicated and written in a very specific language. Traditional parsers are demonstrating relatively small productivity here. In this article, we are demonstrating an opposite approach: ontology-based entailing of words in combination with simple shallow parsing rules. It allows us to increase UAS metrics from 0.82 for SpaCy to 0.834 for our approach.