@inproceedings{smidt-etal-2024-crossroad,
title = "At the Crossroad of Cuneiform and {NLP}: Challenges for Fine-grained Part-of-speech Tagging",
author = "Smidt, Gustav Ryberg and
Lefever, Els and
de Graef, Katrien",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.154/",
pages = "1745--1755",
abstract = "The study of ancient Middle Eastern cultures is dominated by the vast number of cuneiform texts. Multiple languages and language families were expressed in cuneiform. The most dominant language written in cuneiform is the Semitic Akkadian, which is the focus of this paper. We are specifically focusing on letters written in the dialect used in modern-day Baghdad and south towards the Persian Gulf during the Old Babylonian period (c. 2000-1600 B.C.E.). The Akkadian language was rediscovered in the 19th century and is now being scrutinised by Natural Language Processing (NLP) methods. However, existing Akkadian text publications are not always suitable for digital editions. We therefore risk applying NLP methods onto renderings of Akkadian unfit for the purpose. In this paper we want to investigate the input material and try to initiate a discussion about best-practices in the crossroad where NLP meets cuneiform studies. Specifically, we want to question the use of pre-trained embeddings, sentence segmentation and the type of cuneiform input used to fine-tune language models for the task of fine-grained part-of-speech tagging. We examine the issues by theoretical and practical approaches in a way that we hope spurs discussions that are relevant for automatic processing of other ancient languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="smidt-etal-2024-crossroad">
<titleInfo>
<title>At the Crossroad of Cuneiform and NLP: Challenges for Fine-grained Part-of-speech Tagging</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gustav</namePart>
<namePart type="given">Ryberg</namePart>
<namePart type="family">Smidt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Els</namePart>
<namePart type="family">Lefever</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katrien</namePart>
<namePart type="family">de Graef</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The study of ancient Middle Eastern cultures is dominated by the vast number of cuneiform texts. Multiple languages and language families were expressed in cuneiform. The most dominant language written in cuneiform is the Semitic Akkadian, which is the focus of this paper. We are specifically focusing on letters written in the dialect used in modern-day Baghdad and south towards the Persian Gulf during the Old Babylonian period (c. 2000-1600 B.C.E.). The Akkadian language was rediscovered in the 19th century and is now being scrutinised by Natural Language Processing (NLP) methods. However, existing Akkadian text publications are not always suitable for digital editions. We therefore risk applying NLP methods onto renderings of Akkadian unfit for the purpose. In this paper we want to investigate the input material and try to initiate a discussion about best-practices in the crossroad where NLP meets cuneiform studies. Specifically, we want to question the use of pre-trained embeddings, sentence segmentation and the type of cuneiform input used to fine-tune language models for the task of fine-grained part-of-speech tagging. We examine the issues by theoretical and practical approaches in a way that we hope spurs discussions that are relevant for automatic processing of other ancient languages.</abstract>
<identifier type="citekey">smidt-etal-2024-crossroad</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.154/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>1745</start>
<end>1755</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T At the Crossroad of Cuneiform and NLP: Challenges for Fine-grained Part-of-speech Tagging
%A Smidt, Gustav Ryberg
%A Lefever, Els
%A de Graef, Katrien
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F smidt-etal-2024-crossroad
%X The study of ancient Middle Eastern cultures is dominated by the vast number of cuneiform texts. Multiple languages and language families were expressed in cuneiform. The most dominant language written in cuneiform is the Semitic Akkadian, which is the focus of this paper. We are specifically focusing on letters written in the dialect used in modern-day Baghdad and south towards the Persian Gulf during the Old Babylonian period (c. 2000-1600 B.C.E.). The Akkadian language was rediscovered in the 19th century and is now being scrutinised by Natural Language Processing (NLP) methods. However, existing Akkadian text publications are not always suitable for digital editions. We therefore risk applying NLP methods onto renderings of Akkadian unfit for the purpose. In this paper we want to investigate the input material and try to initiate a discussion about best-practices in the crossroad where NLP meets cuneiform studies. Specifically, we want to question the use of pre-trained embeddings, sentence segmentation and the type of cuneiform input used to fine-tune language models for the task of fine-grained part-of-speech tagging. We examine the issues by theoretical and practical approaches in a way that we hope spurs discussions that are relevant for automatic processing of other ancient languages.
%U https://aclanthology.org/2024.lrec-main.154/
%P 1745-1755
Markdown (Informal)
[At the Crossroad of Cuneiform and NLP: Challenges for Fine-grained Part-of-speech Tagging](https://aclanthology.org/2024.lrec-main.154/) (Smidt et al., LREC-COLING 2024)
ACL