# Latin writing styles analysis with Machine Learning: New approach to old questions

arXiv: https://arxiv.org/abs/2109.00601 · HTML: https://mlsanity.com/paper/2109.00601/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 21 references that are in the map.
- First posted on arXiv 1 Sep 2021.

## Builds on (most cited first, 6 of 6)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [Latin BERT: A Contextual Language Model for Classical Philology](https://mlsanity.com/paper/2009.10053/) (2020)
- [Integrated Sequence Tagging for Medieval Latin Using Deep Representation Learning](https://mlsanity.com/paper/1603.01597/) (2016)

## Built on by (most cited first, 1 of 1)

- [Loci Similes: A Benchmark for Extracting Intertextualities in Latin Literature](https://mlsanity.com/paper/2601.07533/) (2026)

## Abstract (arXiv)

In the Middle Ages texts were learned by heart and spread using oral means of communication from generation to generation. Adaptation of the art of prose and poems allowed keeping particular descriptions and compositions characteristic for many literary genres. Taking into account such a specific construction of literature composed in Latin, we can search for and indicate the probability patterns of familiar sources of specific narrative texts. Consideration of Natural Language Processing tools allowed us the transformation of textual objects into numerical ones and then application of machine learning algorithms to extract information from the dataset. We carried out the task consisting of the practical use of those concepts and observation to create a tool for analyzing narrative texts basing on open-source databases. The tool focused on creating specific search tools resources which could enable us detailed searching throughout the text. The main objectives of the study take into account finding similarities between sentences and between documents. Next, we applied machine learning algorithms on chosen texts to calculate specific features of them (for instance authorship or centuries) and to recognize sources of anonymous texts with a certain percentage.