Natural language processing and discourse complexity studies

The study presents an overview of discursive complexology, integral paradigm linguistics, cognitive studies and computer linguistics aimed at defining discourse complexity. article comprises three main parts, which successively outline views on the category linguistic complexity, history complexology modern methods text complexity assessment. Distinguishing concepts we recognize absolute nature assessment relative determined by abilities a recipient. Founded in 19th century, theory is still focused validating predictors criteria for perception difficulty. We briefly characterize five previous stages complexology: formative, classical, period closed tests, constructive-cognitive natural language processing. also present theoretical foundations Coh-Metrix, automatic analyzer, based five-level model perception. Computing not only lexical syntactic parameters, but level situational models rhetorical structures, Coh-Metrix provides high accuracy show benefits processing wide range application areas profilers digital platforms such as LEXILE ReaderBench. view parametrization development matrix texts various genres nearest prospect may enable higher inter- intra-linguistic contrastive studies, well automating selection modification pragmatic purposes.