@inproceedings{keersmaekers-2021-glaux,
title = "The {GLAU}x corpus: methodological issues in designing a long-term, diverse, multi-layered corpus of {A}ncient {G}reek",
author = "Keersmaekers, Alek",
editor = "Tahmasebi, Nina and
Jatowt, Adam and
Xu, Yang and
Hengchen, Simon and
Montariol, Syrielle and
Dubossarsky, Haim",
booktitle = "Proceedings of the 2nd International Workshop on Computational Approaches to Historical Language Change 2021",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.lchange-1.6",
doi = "10.18653/v1/2021.lchange-1.6",
pages = "39--50",
abstract = "This paper describes the GLAUx project ({``}the Greek Language Automated{''}), an ongoing effort to develop a large long-term diachronic corpus of Greek, covering sixteen centuries of literary and non-literary material annotated with NLP methods. After providing an overview of related corpus projects and discussing the general architecture of the corpus, it zooms in on a number of larger methodological issues in the design of historical corpora. These include the encoding of textual variants, handling extralinguistic variation and annotating linguistic ambiguity. Finally, the long- and short-term perspectives of this project are discussed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="keersmaekers-2021-glaux">
<titleInfo>
<title>The GLAUx corpus: methodological issues in designing a long-term, diverse, multi-layered corpus of Ancient Greek</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alek</namePart>
<namePart type="family">Keersmaekers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd International Workshop on Computational Approaches to Historical Language Change 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="family">Tahmasebi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Jatowt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Hengchen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Syrielle</namePart>
<namePart type="family">Montariol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haim</namePart>
<namePart type="family">Dubossarsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the GLAUx project (“the Greek Language Automated”), an ongoing effort to develop a large long-term diachronic corpus of Greek, covering sixteen centuries of literary and non-literary material annotated with NLP methods. After providing an overview of related corpus projects and discussing the general architecture of the corpus, it zooms in on a number of larger methodological issues in the design of historical corpora. These include the encoding of textual variants, handling extralinguistic variation and annotating linguistic ambiguity. Finally, the long- and short-term perspectives of this project are discussed.</abstract>
<identifier type="citekey">keersmaekers-2021-glaux</identifier>
<identifier type="doi">10.18653/v1/2021.lchange-1.6</identifier>
<location>
<url>https://aclanthology.org/2021.lchange-1.6</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>39</start>
<end>50</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The GLAUx corpus: methodological issues in designing a long-term, diverse, multi-layered corpus of Ancient Greek
%A Keersmaekers, Alek
%Y Tahmasebi, Nina
%Y Jatowt, Adam
%Y Xu, Yang
%Y Hengchen, Simon
%Y Montariol, Syrielle
%Y Dubossarsky, Haim
%S Proceedings of the 2nd International Workshop on Computational Approaches to Historical Language Change 2021
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F keersmaekers-2021-glaux
%X This paper describes the GLAUx project (“the Greek Language Automated”), an ongoing effort to develop a large long-term diachronic corpus of Greek, covering sixteen centuries of literary and non-literary material annotated with NLP methods. After providing an overview of related corpus projects and discussing the general architecture of the corpus, it zooms in on a number of larger methodological issues in the design of historical corpora. These include the encoding of textual variants, handling extralinguistic variation and annotating linguistic ambiguity. Finally, the long- and short-term perspectives of this project are discussed.
%R 10.18653/v1/2021.lchange-1.6
%U https://aclanthology.org/2021.lchange-1.6
%U https://doi.org/10.18653/v1/2021.lchange-1.6
%P 39-50
Markdown (Informal)
[The GLAUx corpus: methodological issues in designing a long-term, diverse, multi-layered corpus of Ancient Greek](https://aclanthology.org/2021.lchange-1.6) (Keersmaekers, LChange 2021)
ACL