@inproceedings{de-graaf-etal-2022-agile,
title = "{AGIL}e: The First Lemmatizer for {A}ncient {G}reek Inscriptions",
author = "de Graaf, Evelien and
Stopponi, Silvia and
Bos, Jasper K. and
Peels-Matthey, Saskia and
Nissim, Malvina",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.571/",
pages = "5334--5344",
abstract = "To facilitate corpus searches by classicists as well as to reduce data sparsity when training models, we focus on the automatic lemmatization of ancient Greek inscriptions, which have not received as much attention in this sense as literary text data has. We show that existing lemmatizers for ancient Greek, trained on literary data, are not performant on epigraphic data, due to major language differences between the two types of texts. We thus train the first inscription-specific lemmatizer achieving above 80{\%} accuracy, and make both the models and the lemmatized data available to the community. We also provide a detailed error analysis highlighting peculiarities of inscriptions which again highlights the importance of a lemmatizer dedicated to inscriptions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-graaf-etal-2022-agile">
<titleInfo>
<title>AGILe: The First Lemmatizer for Ancient Greek Inscriptions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Evelien</namePart>
<namePart type="family">de Graaf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Silvia</namePart>
<namePart type="family">Stopponi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jasper</namePart>
<namePart type="given">K</namePart>
<namePart type="family">Bos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saskia</namePart>
<namePart type="family">Peels-Matthey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malvina</namePart>
<namePart type="family">Nissim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To facilitate corpus searches by classicists as well as to reduce data sparsity when training models, we focus on the automatic lemmatization of ancient Greek inscriptions, which have not received as much attention in this sense as literary text data has. We show that existing lemmatizers for ancient Greek, trained on literary data, are not performant on epigraphic data, due to major language differences between the two types of texts. We thus train the first inscription-specific lemmatizer achieving above 80% accuracy, and make both the models and the lemmatized data available to the community. We also provide a detailed error analysis highlighting peculiarities of inscriptions which again highlights the importance of a lemmatizer dedicated to inscriptions.</abstract>
<identifier type="citekey">de-graaf-etal-2022-agile</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.571/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5334</start>
<end>5344</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AGILe: The First Lemmatizer for Ancient Greek Inscriptions
%A de Graaf, Evelien
%A Stopponi, Silvia
%A Bos, Jasper K.
%A Peels-Matthey, Saskia
%A Nissim, Malvina
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F de-graaf-etal-2022-agile
%X To facilitate corpus searches by classicists as well as to reduce data sparsity when training models, we focus on the automatic lemmatization of ancient Greek inscriptions, which have not received as much attention in this sense as literary text data has. We show that existing lemmatizers for ancient Greek, trained on literary data, are not performant on epigraphic data, due to major language differences between the two types of texts. We thus train the first inscription-specific lemmatizer achieving above 80% accuracy, and make both the models and the lemmatized data available to the community. We also provide a detailed error analysis highlighting peculiarities of inscriptions which again highlights the importance of a lemmatizer dedicated to inscriptions.
%U https://aclanthology.org/2022.lrec-1.571/
%P 5334-5344
Markdown (Informal)
[AGILe: The First Lemmatizer for Ancient Greek Inscriptions](https://aclanthology.org/2022.lrec-1.571/) (de Graaf et al., LREC 2022)
ACL
- Evelien de Graaf, Silvia Stopponi, Jasper K. Bos, Saskia Peels-Matthey, and Malvina Nissim. 2022. AGILe: The First Lemmatizer for Ancient Greek Inscriptions. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 5334–5344, Marseille, France. European Language Resources Association.