Part of
Language and Text: Data, models, information and applicationsEdited by Adam Pawłowski, Jan Mačutek, Sheila Embleton and George Mikros
[Current Issues in Linguistic Theory 356] 2021
► pp. 145–162
We present a study of the distinctiveness of random and non-random texts based on text characteristics of quantitative linguistics. We additionally experiment with text features that evaluate contiguity associations among sentences by means of BERT (Bidirectional Encoder Representations from Transformers). To this end, we experiment with generative models for random texts as currently discussed in the context of neural networks. The chapter contributes to the clarification of deficits of existing random text models and of the informativeness of quantitative text features.