Saved in:
Bibliographic Details
Main Authors: Atzenhofer-Baumgartner, Florian, Kovács, Tamás
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.16446
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909700357881856
author Atzenhofer-Baumgartner, Florian
Kovács, Tamás
author_facet Atzenhofer-Baumgartner, Florian
Kovács, Tamás
contents This study examines the impact of historical text normalization on the classification of medieval charters, specifically focusing on document dating and locating. Using a data set of Middle High German charters from a digital archive, we evaluate various classifiers, including traditional and transformer-based models, with and without normalization. Our results indicate that the given normalization minimally improves locating tasks but reduces accuracy for dating, implying that original texts contain crucial features that normalization may obscure. We find that support vector machines and gradient boosting outperform other models, questioning the efficiency of transformers for this use case. Results suggest a selective approach to historical text normalization, emphasizing the significance of preserving some textual characteristics that are critical for classification tasks in document analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2408_16446
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Is text normalization relevant for classifying medieval charters?
Atzenhofer-Baumgartner, Florian
Kovács, Tamás
Computation and Language
Information Retrieval
This study examines the impact of historical text normalization on the classification of medieval charters, specifically focusing on document dating and locating. Using a data set of Middle High German charters from a digital archive, we evaluate various classifiers, including traditional and transformer-based models, with and without normalization. Our results indicate that the given normalization minimally improves locating tasks but reduces accuracy for dating, implying that original texts contain crucial features that normalization may obscure. We find that support vector machines and gradient boosting outperform other models, questioning the efficiency of transformers for this use case. Results suggest a selective approach to historical text normalization, emphasizing the significance of preserving some textual characteristics that are critical for classification tasks in document analysis.
title Is text normalization relevant for classifying medieval charters?
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2408.16446