@inproceedings{simmons-etal-2024-sumtablets,
title = "{S}um{T}ablets: A Transliteration Dataset of {S}umerian Tablets",
author = "Simmons, Cole and
Diehl Martinez, Richard and
Jurafsky, Dan",
editor = "Pavlopoulos, John and
Sommerschield, Thea and
Assael, Yannis and
Gordin, Shai and
Cho, Kyunghyun and
Passarotti, Marco and
Sprugnoli, Rachele and
Liu, Yudong and
Li, Bin and
Anderson, Adam",
booktitle = "Proceedings of the 1st Workshop on Machine Learning for Ancient Languages (ML4AL 2024)",
month = aug,
year = "2024",
address = "Hybrid in Bangkok, Thailand and online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.ml4al-1.20",
doi = "10.18653/v1/2024.ml4al-1.20",
pages = "192--202",
abstract = "Transliterating Sumerian is a key step in understanding Sumerian texts, but remains a difficult and time-consuming task. With more than 100,000 known texts and comparatively few specialists, manually maintaining up-to-date transliterations for the entire corpus is impractical. While many transliterations have been published online thanks to the dedicated effort of previous projects, the lack of a comprehensive, easily accessible dataset that pairs digital representations of source glyphs with their transliterations has hindered the application of natural language processing (NLP) methods to this task.To address this gap, we present SumTablets, the largest collection of Sumerian cuneiform tablets structured as Unicode glyph{--}transliteration pairs. Our dataset comprises 91,606 tablets (totaling 6,970,407 glyphs) with associated period and genre metadata. We release SumTablets as a Hugging Face Dataset.To construct SumTablets, we first preprocess and standardize publicly available transliterations. We then map them back to a Unicode representation of their source glyphs, retaining parallel structural information (e.g., surfaces, newlines, broken segments) through the use of special tokens.We leverage SumTablets to implement and evaluate two transliteration approaches: 1) weighted sampling from a glyph{'}s possible readings, 2) fine-tuning an autoregressive language model. Our fine-tuned language model achieves an average transliteration character-level F-score (chrF) of 97.55, demonstrating the potential use of deep learning methods in Assyriological research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="simmons-etal-2024-sumtablets">
<titleInfo>
<title>SumTablets: A Transliteration Dataset of Sumerian Tablets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cole</namePart>
<namePart type="family">Simmons</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Diehl Martinez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Machine Learning for Ancient Languages (ML4AL 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Pavlopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thea</namePart>
<namePart type="family">Sommerschield</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yannis</namePart>
<namePart type="family">Assael</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">Kyunghyun</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</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>
<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">Bin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Anderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hybrid in Bangkok, Thailand and online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Transliterating Sumerian is a key step in understanding Sumerian texts, but remains a difficult and time-consuming task. With more than 100,000 known texts and comparatively few specialists, manually maintaining up-to-date transliterations for the entire corpus is impractical. While many transliterations have been published online thanks to the dedicated effort of previous projects, the lack of a comprehensive, easily accessible dataset that pairs digital representations of source glyphs with their transliterations has hindered the application of natural language processing (NLP) methods to this task.To address this gap, we present SumTablets, the largest collection of Sumerian cuneiform tablets structured as Unicode glyph–transliteration pairs. Our dataset comprises 91,606 tablets (totaling 6,970,407 glyphs) with associated period and genre metadata. We release SumTablets as a Hugging Face Dataset.To construct SumTablets, we first preprocess and standardize publicly available transliterations. We then map them back to a Unicode representation of their source glyphs, retaining parallel structural information (e.g., surfaces, newlines, broken segments) through the use of special tokens.We leverage SumTablets to implement and evaluate two transliteration approaches: 1) weighted sampling from a glyph’s possible readings, 2) fine-tuning an autoregressive language model. Our fine-tuned language model achieves an average transliteration character-level F-score (chrF) of 97.55, demonstrating the potential use of deep learning methods in Assyriological research.</abstract>
<identifier type="citekey">simmons-etal-2024-sumtablets</identifier>
<identifier type="doi">10.18653/v1/2024.ml4al-1.20</identifier>
<location>
<url>https://aclanthology.org/2024.ml4al-1.20</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>192</start>
<end>202</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SumTablets: A Transliteration Dataset of Sumerian Tablets
%A Simmons, Cole
%A Diehl Martinez, Richard
%A Jurafsky, Dan
%Y Pavlopoulos, John
%Y Sommerschield, Thea
%Y Assael, Yannis
%Y Gordin, Shai
%Y Cho, Kyunghyun
%Y Passarotti, Marco
%Y Sprugnoli, Rachele
%Y Liu, Yudong
%Y Li, Bin
%Y Anderson, Adam
%S Proceedings of the 1st Workshop on Machine Learning for Ancient Languages (ML4AL 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Hybrid in Bangkok, Thailand and online
%F simmons-etal-2024-sumtablets
%X Transliterating Sumerian is a key step in understanding Sumerian texts, but remains a difficult and time-consuming task. With more than 100,000 known texts and comparatively few specialists, manually maintaining up-to-date transliterations for the entire corpus is impractical. While many transliterations have been published online thanks to the dedicated effort of previous projects, the lack of a comprehensive, easily accessible dataset that pairs digital representations of source glyphs with their transliterations has hindered the application of natural language processing (NLP) methods to this task.To address this gap, we present SumTablets, the largest collection of Sumerian cuneiform tablets structured as Unicode glyph–transliteration pairs. Our dataset comprises 91,606 tablets (totaling 6,970,407 glyphs) with associated period and genre metadata. We release SumTablets as a Hugging Face Dataset.To construct SumTablets, we first preprocess and standardize publicly available transliterations. We then map them back to a Unicode representation of their source glyphs, retaining parallel structural information (e.g., surfaces, newlines, broken segments) through the use of special tokens.We leverage SumTablets to implement and evaluate two transliteration approaches: 1) weighted sampling from a glyph’s possible readings, 2) fine-tuning an autoregressive language model. Our fine-tuned language model achieves an average transliteration character-level F-score (chrF) of 97.55, demonstrating the potential use of deep learning methods in Assyriological research.
%R 10.18653/v1/2024.ml4al-1.20
%U https://aclanthology.org/2024.ml4al-1.20
%U https://doi.org/10.18653/v1/2024.ml4al-1.20
%P 192-202
Markdown (Informal)
[SumTablets: A Transliteration Dataset of Sumerian Tablets](https://aclanthology.org/2024.ml4al-1.20) (Simmons et al., ML4AL-WS 2024)
ACL
- Cole Simmons, Richard Diehl Martinez, and Dan Jurafsky. 2024. SumTablets: A Transliteration Dataset of Sumerian Tablets. In Proceedings of the 1st Workshop on Machine Learning for Ancient Languages (ML4AL 2024), pages 192–202, Hybrid in Bangkok, Thailand and online. Association for Computational Linguistics.