@inproceedings{yavasan-gordin-2025-clay,
title = "From Clay to Code: Transforming {H}ittite Texts for Machine Learning",
author = "Yavasan, Emma and
Gordin, Shai",
editor = "Anderson, Adam and
Gordin, Shai and
Li, Bin and
Liu, Yudong and
Passarotti, Marco C. and
Sprugnoli, Rachele",
booktitle = "Proceedings of the Second Workshop on Ancient Language Processing",
month = may,
year = "2025",
address = "The Albuquerque Convention Center, Laguna",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.alp-1.10/",
doi = "10.18653/v1/2025.alp-1.10",
pages = "77--86",
ISBN = "979-8-89176-235-0",
abstract = "This paper presents a comprehensive method-ology for transforming XML-encoded Hittite cuneiform texts into computationally accessi-ble formats for machine learning applications. Drawing from a corpus of 8,898 texts (558,349 tokens in total) encompassing 145 cataloged genres and compositions, we develop a struc-tured approach to preserve both linguistic and philological annotations while enabling compu-tational analysis. Our methodology addresses key challenges in ancient language processing, including the handling of fragmentary texts, multiple language layers, and complex anno-tation systems. We demonstrate the applica-tion of our corpus through experiments with T5 models, achieving significant improvements in Hittite-to-German translation (ROUGE-1: 0.895) while identifying limitations in morpho-logical glossing tasks. This work establishes a standardized, machine-readable dataset in Hit-tite cuneiform, which also maintains a balance with philological accuracy and current state-of-the-art."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yavasan-gordin-2025-clay">
<titleInfo>
<title>From Clay to Code: Transforming Hittite Texts for Machine Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emma</namePart>
<namePart type="family">Yavasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shai</namePart>
<namePart type="family">Gordin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Ancient Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Anderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shai</namePart>
<namePart type="family">Gordin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yudong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Passarotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">The Albuquerque Convention Center, Laguna</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-235-0</identifier>
</relatedItem>
<abstract>This paper presents a comprehensive method-ology for transforming XML-encoded Hittite cuneiform texts into computationally accessi-ble formats for machine learning applications. Drawing from a corpus of 8,898 texts (558,349 tokens in total) encompassing 145 cataloged genres and compositions, we develop a struc-tured approach to preserve both linguistic and philological annotations while enabling compu-tational analysis. Our methodology addresses key challenges in ancient language processing, including the handling of fragmentary texts, multiple language layers, and complex anno-tation systems. We demonstrate the applica-tion of our corpus through experiments with T5 models, achieving significant improvements in Hittite-to-German translation (ROUGE-1: 0.895) while identifying limitations in morpho-logical glossing tasks. This work establishes a standardized, machine-readable dataset in Hit-tite cuneiform, which also maintains a balance with philological accuracy and current state-of-the-art.</abstract>
<identifier type="citekey">yavasan-gordin-2025-clay</identifier>
<identifier type="doi">10.18653/v1/2025.alp-1.10</identifier>
<location>
<url>https://aclanthology.org/2025.alp-1.10/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>77</start>
<end>86</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Clay to Code: Transforming Hittite Texts for Machine Learning
%A Yavasan, Emma
%A Gordin, Shai
%Y Anderson, Adam
%Y Gordin, Shai
%Y Li, Bin
%Y Liu, Yudong
%Y Passarotti, Marco C.
%Y Sprugnoli, Rachele
%S Proceedings of the Second Workshop on Ancient Language Processing
%D 2025
%8 May
%I Association for Computational Linguistics
%C The Albuquerque Convention Center, Laguna
%@ 979-8-89176-235-0
%F yavasan-gordin-2025-clay
%X This paper presents a comprehensive method-ology for transforming XML-encoded Hittite cuneiform texts into computationally accessi-ble formats for machine learning applications. Drawing from a corpus of 8,898 texts (558,349 tokens in total) encompassing 145 cataloged genres and compositions, we develop a struc-tured approach to preserve both linguistic and philological annotations while enabling compu-tational analysis. Our methodology addresses key challenges in ancient language processing, including the handling of fragmentary texts, multiple language layers, and complex anno-tation systems. We demonstrate the applica-tion of our corpus through experiments with T5 models, achieving significant improvements in Hittite-to-German translation (ROUGE-1: 0.895) while identifying limitations in morpho-logical glossing tasks. This work establishes a standardized, machine-readable dataset in Hit-tite cuneiform, which also maintains a balance with philological accuracy and current state-of-the-art.
%R 10.18653/v1/2025.alp-1.10
%U https://aclanthology.org/2025.alp-1.10/
%U https://doi.org/10.18653/v1/2025.alp-1.10
%P 77-86
Markdown (Informal)
[From Clay to Code: Transforming Hittite Texts for Machine Learning](https://aclanthology.org/2025.alp-1.10/) (Yavasan & Gordin, ALP 2025)
ACL