Saved in:
Bibliographic Details
Main Authors: Schöffel, Matthias, Wiedner, Marinus, Arias, Esteban Garces, Ruppert, Paula, Heumann, Christian, Aßenmacher, Matthias
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.07827
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915190104129536
author Schöffel, Matthias
Wiedner, Marinus
Arias, Esteban Garces
Ruppert, Paula
Heumann, Christian
Aßenmacher, Matthias
author_facet Schöffel, Matthias
Wiedner, Marinus
Arias, Esteban Garces
Ruppert, Paula
Heumann, Christian
Aßenmacher, Matthias
contents Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing, yet their effectiveness in handling historical languages remains largely unexplored. This study examines the performance of open-source LLMs in part-of-speech (POS) tagging for Old Occitan, a historical language characterized by non-standardized orthography and significant diachronic variation. Through comparative analysis of two distinct corpora-hagiographical and medical texts-we evaluate how current models handle the inherent challenges of processing a low-resource historical language. Our findings demonstrate critical limitations in LLM performance when confronted with extreme orthographic and syntactic variability. We provide detailed error analysis and specific recommendations for improving model performance in historical language processing. This research advances our understanding of LLM capabilities in challenging linguistic contexts while offering practical insights for both computational linguistics and historical language studies.
format Preprint
id arxiv_https___arxiv_org_abs_2503_07827
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Modern Models, Medieval Texts: A POS Tagging Study of Old Occitan
Schöffel, Matthias
Wiedner, Marinus
Arias, Esteban Garces
Ruppert, Paula
Heumann, Christian
Aßenmacher, Matthias
Computation and Language
Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing, yet their effectiveness in handling historical languages remains largely unexplored. This study examines the performance of open-source LLMs in part-of-speech (POS) tagging for Old Occitan, a historical language characterized by non-standardized orthography and significant diachronic variation. Through comparative analysis of two distinct corpora-hagiographical and medical texts-we evaluate how current models handle the inherent challenges of processing a low-resource historical language. Our findings demonstrate critical limitations in LLM performance when confronted with extreme orthographic and syntactic variability. We provide detailed error analysis and specific recommendations for improving model performance in historical language processing. This research advances our understanding of LLM capabilities in challenging linguistic contexts while offering practical insights for both computational linguistics and historical language studies.
title Modern Models, Medieval Texts: A POS Tagging Study of Old Occitan
topic Computation and Language
url https://arxiv.org/abs/2503.07827