Abstract
<jats:title>Abstract</jats:title> <jats:p> The study <jats:italic>In Between Primordial Language and NLP Architecting</jats:italic> is a multi-part study that presents an outcome of broader research that emerged at the crossroads of two projects: <jats:italic>Assessing Neoplatonism in the 14th and 15th Balkans</jats:italic> (supported by the Science Fund of the Republic of Serbia, Grant No 1554), and <jats:italic>Linguistic Research of Contemporary Serbian Literary Language and the Development of the SASA Dictionary of the Serbo-Croatian Literary and Vernacular Language</jats:italic> (funded by the Ministry of Science, Technological Development and Innovation of the Republic of Serbia, Registration No 451-03-66/2024-03/200174) having continued to develop as a discrete subproject with the main research goal to enlarge knowledge regarding the possibilities of transforming, adjusting and modifying fittingly the primordial <jats:italic>codes of linguae</jats:italic> as a <jats:italic>“livingˮ entity</jats:italic> through various so-called NLP architecture to an <jats:italic>epigenetic linguae</jats:italic> as a single undivided entity or whole so that its “good or bad sides emergingˮ could be predicted primarily in a comparative perspective. This paper represents the first part of the comprehensive study and refers to the first part of the title of the study, <jats:italic>i.e.</jats:italic> of its reference context and hints at the directions in which this still unfinished research regarding how a natural language processing (NLP) system can be built using a variety of architectures, including rule-based systems, statistical models, and neural networks ( <jats:xref>Sharma 2023</jats:xref> ). </jats:p>