@inproceedings{nikolova-stoupak-etal-2024-compilation,
title = "Compilation of a Synthetic {J}udeo-{F}rench Corpus",
author = "Nikolova-Stoupak, Iglika and
Lejeune, Ga{\'e}l and
Schaeffer-Lacroix, Eva",
editor = "Bizzoni, Yuri and
Degaetano-Ortlieb, Stefania and
Kazantseva, Anna and
Szpakowicz, Stan",
booktitle = "Proceedings of the 8th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2024)",
month = mar,
year = "2024",
address = "St. Julians, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.latechclfl-1.5",
pages = "40--45",
abstract = "This is a short paper describing the process of derivation of synthetic Judeo-French text. Judeo-French is one of a number of rare languages used in speaking and writing by Jewish communities as confined to a particular temporal and geographical frame (in this case, 11th- to 14th-century France). The number of resources in the language is very limited and its involvement in the contemporary domain of Natural Language Processing (NLP) is practically non-existent. This work outlines the compilation of a synthetic Judeo-French corpus. For the purpose, a pipeline of transformations is applied to Old French text belonging to the same general time period, leading to the derivation of text that is as reliable as possible in terms of phonological, morphological and lexical characteristics as witnessed in Judeo-French. Ultimately, the goal is for this synthetic corpus to be used in standard NLP tasks, such as Neural Machine Translation (NMT), as an instance of data augmentation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nikolova-stoupak-etal-2024-compilation">
<titleInfo>
<title>Compilation of a Synthetic Judeo-French Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iglika</namePart>
<namePart type="family">Nikolova-Stoupak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaél</namePart>
<namePart type="family">Lejeune</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Schaeffer-Lacroix</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefania</namePart>
<namePart type="family">Degaetano-Ortlieb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Kazantseva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stan</namePart>
<namePart type="family">Szpakowicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julians, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This is a short paper describing the process of derivation of synthetic Judeo-French text. Judeo-French is one of a number of rare languages used in speaking and writing by Jewish communities as confined to a particular temporal and geographical frame (in this case, 11th- to 14th-century France). The number of resources in the language is very limited and its involvement in the contemporary domain of Natural Language Processing (NLP) is practically non-existent. This work outlines the compilation of a synthetic Judeo-French corpus. For the purpose, a pipeline of transformations is applied to Old French text belonging to the same general time period, leading to the derivation of text that is as reliable as possible in terms of phonological, morphological and lexical characteristics as witnessed in Judeo-French. Ultimately, the goal is for this synthetic corpus to be used in standard NLP tasks, such as Neural Machine Translation (NMT), as an instance of data augmentation.</abstract>
<identifier type="citekey">nikolova-stoupak-etal-2024-compilation</identifier>
<location>
<url>https://aclanthology.org/2024.latechclfl-1.5</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>40</start>
<end>45</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Compilation of a Synthetic Judeo-French Corpus
%A Nikolova-Stoupak, Iglika
%A Lejeune, Gaél
%A Schaeffer-Lacroix, Eva
%Y Bizzoni, Yuri
%Y Degaetano-Ortlieb, Stefania
%Y Kazantseva, Anna
%Y Szpakowicz, Stan
%S Proceedings of the 8th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2024)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julians, Malta
%F nikolova-stoupak-etal-2024-compilation
%X This is a short paper describing the process of derivation of synthetic Judeo-French text. Judeo-French is one of a number of rare languages used in speaking and writing by Jewish communities as confined to a particular temporal and geographical frame (in this case, 11th- to 14th-century France). The number of resources in the language is very limited and its involvement in the contemporary domain of Natural Language Processing (NLP) is practically non-existent. This work outlines the compilation of a synthetic Judeo-French corpus. For the purpose, a pipeline of transformations is applied to Old French text belonging to the same general time period, leading to the derivation of text that is as reliable as possible in terms of phonological, morphological and lexical characteristics as witnessed in Judeo-French. Ultimately, the goal is for this synthetic corpus to be used in standard NLP tasks, such as Neural Machine Translation (NMT), as an instance of data augmentation.
%U https://aclanthology.org/2024.latechclfl-1.5
%P 40-45
Markdown (Informal)
[Compilation of a Synthetic Judeo-French Corpus](https://aclanthology.org/2024.latechclfl-1.5) (Nikolova-Stoupak et al., LaTeCHCLfL-WS 2024)
ACL
- Iglika Nikolova-Stoupak, Gaél Lejeune, and Eva Schaeffer-Lacroix. 2024. Compilation of a Synthetic Judeo-French Corpus. In Proceedings of the 8th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2024), pages 40–45, St. Julians, Malta. Association for Computational Linguistics.