@inproceedings{yousef-etal-2023-named,
title = "Named Entity Annotation Projection Applied to Classical Languages",
author = {Yousef, Tariq and
Palladino, Chiara and
Heyer, Gerhard and
J{\"a}nicke, Stefan},
editor = "Degaetano-Ortlieb, Stefania and
Kazantseva, Anna and
Reiter, Nils and
Szpakowicz, Stan",
booktitle = "Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.latechclfl-1.19",
doi = "10.18653/v1/2023.latechclfl-1.19",
pages = "175--182",
abstract = "In this study, we demonstrate how to apply cross-lingual annotation projection to transfer named-entity annotations to classical languages for which limited or no resources and annotated texts are available, aiming to enrich their NER training datasets and train a model to perform NER tagging. Our method uses sentence-level aligned parallel corpora ancient texts and the translation in a modern language, for which high-quality off-the-shelf NER systems are available. We automatically annotate the text of the modern language and employ a state-of-the-art neural word alignment system to find translation equivalents. Finally, we transfer the annotations to the corresponding tokens in the ancient texts using a direct projection heuristic. We applied our method to ancient Greek, Latin, and Arabic using the Bible with the English translation as a parallel corpus. We used the resulting annotations to enhance the performance of an existing NER model for ancient Greek",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yousef-etal-2023-named">
<titleInfo>
<title>Named Entity Annotation Projection Applied to Classical Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tariq</namePart>
<namePart type="family">Yousef</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chiara</namePart>
<namePart type="family">Palladino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerhard</namePart>
<namePart type="family">Heyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Jänicke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature</title>
</titleInfo>
<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">Nils</namePart>
<namePart type="family">Reiter</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">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this study, we demonstrate how to apply cross-lingual annotation projection to transfer named-entity annotations to classical languages for which limited or no resources and annotated texts are available, aiming to enrich their NER training datasets and train a model to perform NER tagging. Our method uses sentence-level aligned parallel corpora ancient texts and the translation in a modern language, for which high-quality off-the-shelf NER systems are available. We automatically annotate the text of the modern language and employ a state-of-the-art neural word alignment system to find translation equivalents. Finally, we transfer the annotations to the corresponding tokens in the ancient texts using a direct projection heuristic. We applied our method to ancient Greek, Latin, and Arabic using the Bible with the English translation as a parallel corpus. We used the resulting annotations to enhance the performance of an existing NER model for ancient Greek</abstract>
<identifier type="citekey">yousef-etal-2023-named</identifier>
<identifier type="doi">10.18653/v1/2023.latechclfl-1.19</identifier>
<location>
<url>https://aclanthology.org/2023.latechclfl-1.19</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>175</start>
<end>182</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Named Entity Annotation Projection Applied to Classical Languages
%A Yousef, Tariq
%A Palladino, Chiara
%A Heyer, Gerhard
%A Jänicke, Stefan
%Y Degaetano-Ortlieb, Stefania
%Y Kazantseva, Anna
%Y Reiter, Nils
%Y Szpakowicz, Stan
%S Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F yousef-etal-2023-named
%X In this study, we demonstrate how to apply cross-lingual annotation projection to transfer named-entity annotations to classical languages for which limited or no resources and annotated texts are available, aiming to enrich their NER training datasets and train a model to perform NER tagging. Our method uses sentence-level aligned parallel corpora ancient texts and the translation in a modern language, for which high-quality off-the-shelf NER systems are available. We automatically annotate the text of the modern language and employ a state-of-the-art neural word alignment system to find translation equivalents. Finally, we transfer the annotations to the corresponding tokens in the ancient texts using a direct projection heuristic. We applied our method to ancient Greek, Latin, and Arabic using the Bible with the English translation as a parallel corpus. We used the resulting annotations to enhance the performance of an existing NER model for ancient Greek
%R 10.18653/v1/2023.latechclfl-1.19
%U https://aclanthology.org/2023.latechclfl-1.19
%U https://doi.org/10.18653/v1/2023.latechclfl-1.19
%P 175-182
Markdown (Informal)
[Named Entity Annotation Projection Applied to Classical Languages](https://aclanthology.org/2023.latechclfl-1.19) (Yousef et al., LaTeCHCLfL 2023)
ACL
- Tariq Yousef, Chiara Palladino, Gerhard Heyer, and Stefan Jänicke. 2023. Named Entity Annotation Projection Applied to Classical Languages. In Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, pages 175–182, Dubrovnik, Croatia. Association for Computational Linguistics.