Texts, corpora, evidence: using a NLP pipeline to examine textual genres

Prof Pascual Pérez-Paredes

Universitat Jaume I, 9 September 2022

In this workshop we will discuss how corpus approaches to textual analysis have increased our understanding of genres and registers. By looking at existing research designs, we will explore both what corpora can and can’t offer to researchers. The main focus of the workshop is to explore the use of ProTool GENTT, a natural processing (NLP) pipeline that makes use of basic machine learning algorithms.