# Detecting Sexual Content at the Sentence Level in First Millennium Latin Texts

arXiv: https://arxiv.org/abs/2309.14974 · HTML: https://mlsanity.com/paper/2309.14974/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 58 references that are in the map.
- First posted on arXiv 25 Sep 2023.

## Builds on (most cited first, 8 of 8)

- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [AllenNLP: A Deep Semantic Natural Language Processing Platform](https://mlsanity.com/paper/1803.07640/) (2018)
- [Latin BERT: A Contextual Language Model for Classical Philology](https://mlsanity.com/paper/2009.10053/) (2020)
- [Improving Lemmatization of Non-Standard Languages with Joint Learning](https://mlsanity.com/paper/1903.06939/) (2019)
- [On the Feasibility of Automated Detection of Allusive Text Reuse](https://mlsanity.com/paper/1905.02973/) (2019)
- [Categorical Metadata Representation for Customized Text Classification](https://mlsanity.com/paper/1902.05196/) (2019)
- [Metre as a stylometric feature in Latin hexameter poetry](https://mlsanity.com/paper/1911.12478/) (2019)
- [Graecia capta ferum victorem cepit. Detecting Latin Allusions to Ancient Greek Literature](https://mlsanity.com/paper/2308.12008/) (2023)

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

- [Behind Closed Words: Creating and Investigating the forePLay Annotated Dataset for Polish Erotic Discourse](https://mlsanity.com/paper/2412.17533/) (2024)

## Abstract (arXiv)

In this study, we propose to evaluate the use of deep learning methods for semantic classification at the sentence level to accelerate the process of corpus building in the field of humanities and linguistics, a traditional and time-consuming task. We introduce a novel corpus comprising around 2500 sentences spanning from 300 BCE to 900 CE including sexual semantics (medical, erotica, etc.). We evaluate various sentence classification approaches and different input embedding layers, and show that all consistently outperform simple token-based searches. We explore the integration of idiolectal and sociolectal metadata embeddings (centuries, author, type of writing), but find that it leads to overfitting. Our results demonstrate the effectiveness of this approach, achieving high precision and true positive rates (TPR) of respectively 70.60% and 86.33% using HAN. We evaluate the impact of the dataset size on the model performances (420 instead of 2013), and show that, while our models perform worse, they still offer a high enough precision and TPR, even without MLM, respectively 69% and 51%. Given the result, we provide an analysis of the attention mechanism as a supporting added value for humanists in order to produce more data.