@inproceedings{simonjetz-etal-2024-reconstruction,
title = "Reconstruction of Cuneiform Literary Texts as Text Matching",
author = "Simonjetz, Fabian and
Laasonen, Jussi and
Cobanoglu, Yunus and
Fraser, Alexander and
Jim{\'e}nez, Enrique",
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.1197",
pages = "13712--13721",
abstract = "Ancient Mesopotamian literature is riddled with gaps, caused by the decay and fragmentation of its writing material, clay tablets. The discovery of overlaps between fragments allows reconstruction to advance, but it is a slow and unsystematic process. Since new pieces are found and digitized constantly, NLP techniques can help to identify fragments and match them with existing text collections to restore complete literary works. We compare a number of approaches and determine that a character-level n-gram-based similarity matching approach works well for this problem, leading to a large speed-up for researchers in Assyriology.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="simonjetz-etal-2024-reconstruction">
<titleInfo>
<title>Reconstruction of Cuneiform Literary Texts as Text Matching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fabian</namePart>
<namePart type="family">Simonjetz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jussi</namePart>
<namePart type="family">Laasonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunus</namePart>
<namePart type="family">Cobanoglu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Fraser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrique</namePart>
<namePart type="family">Jiménez</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>Ancient Mesopotamian literature is riddled with gaps, caused by the decay and fragmentation of its writing material, clay tablets. The discovery of overlaps between fragments allows reconstruction to advance, but it is a slow and unsystematic process. Since new pieces are found and digitized constantly, NLP techniques can help to identify fragments and match them with existing text collections to restore complete literary works. We compare a number of approaches and determine that a character-level n-gram-based similarity matching approach works well for this problem, leading to a large speed-up for researchers in Assyriology.</abstract>
<identifier type="citekey">simonjetz-etal-2024-reconstruction</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1197</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>13712</start>
<end>13721</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reconstruction of Cuneiform Literary Texts as Text Matching
%A Simonjetz, Fabian
%A Laasonen, Jussi
%A Cobanoglu, Yunus
%A Fraser, Alexander
%A Jiménez, Enrique
%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 simonjetz-etal-2024-reconstruction
%X Ancient Mesopotamian literature is riddled with gaps, caused by the decay and fragmentation of its writing material, clay tablets. The discovery of overlaps between fragments allows reconstruction to advance, but it is a slow and unsystematic process. Since new pieces are found and digitized constantly, NLP techniques can help to identify fragments and match them with existing text collections to restore complete literary works. We compare a number of approaches and determine that a character-level n-gram-based similarity matching approach works well for this problem, leading to a large speed-up for researchers in Assyriology.
%U https://aclanthology.org/2024.lrec-main.1197
%P 13712-13721
Markdown (Informal)
[Reconstruction of Cuneiform Literary Texts as Text Matching](https://aclanthology.org/2024.lrec-main.1197) (Simonjetz et al., LREC-COLING 2024)
ACL
- Fabian Simonjetz, Jussi Laasonen, Yunus Cobanoglu, Alexander Fraser, and Enrique Jiménez. 2024. Reconstruction of Cuneiform Literary Texts as Text Matching. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 13712–13721, Torino, Italia. ELRA and ICCL.