Detecting Sexual Content at the Sentence Level in First Millennium Latin Texts - CAMPUS CONDORCET Access content directly
Conference Papers Year : 2024

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

Abstract

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.
Fichier principal
Vignette du fichier
main.pdf (401.77 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04214375 , version 1 (22-09-2023)
hal-04214375 , version 2 (20-03-2024)
hal-04214375 , version 3 (25-03-2024)

Licence

Attribution

Identifiers

Cite

Thibault Clérice. Detecting Sexual Content at the Sentence Level in First Millennium Latin Texts. Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), ELRA Language Resources Association (ELRA); International Committee on Computational Linguistics (ICCL), May 2024, Torino, Italy. ⟨hal-04214375v3⟩
116 View
75 Download

Altmetric

Share

Gmail Facebook X LinkedIn More