@inproceedings{horvath-etal-2022-elte,
title = "{ELTE} Poetry Corpus: A Machine Annotated Database of Canonical {H}ungarian Poetry",
author = {Horv{\'a}th, P{\'e}ter and
Kundr{\'a}th, P{\'e}ter and
Indig, Bal{\'a}zs and
Fellegi, Zs{\'o}fia and
Szl{\'a}vich, Eszter and
Bajz{\'a}t, T{\'\i}mea Borb{\'a}la and
S{\'a}rk{\"o}zi-Lindner, Zs{\'o}fia and
Vida, Bence and
Karabulut, Aslihan and
Tim{\'a}ri, M{\'a}ria and
Palk{\'o}, G{\'a}bor},
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-1.372",
pages = "3471--3478",
abstract = "ELTE Poetry Corpus is a database that stores canonical Hungarian poetry with automatically generated annotations of the poems{'} structural units, grammatical features and sound devices, i.e. rhyme patterns, rhyme pairs, rhythm, alliterations and the main phonological features of words. The corpus has an open access online query tool with several search functions. The paper presents the main stages of the annotation process and the tools used for each stage. The TEI XML format of the different versions of the corpus, each of which contains an increasing number of annotation layers, is presented as well. We have also specified our own XML format for the corpus, slightly different from TEI, in order to make it easier and faster to execute queries on the corpus. We discuss the results of a manual evaluation of the quality of automatic annotation of rhythm, as well as the results of an automatic evaluation of different rule sets used for the automatic annotation of rhyme patterns. Finally, the paper gives an overview of the main functions of the online query tool developed for the corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="horvath-etal-2022-elte">
<titleInfo>
<title>ELTE Poetry Corpus: A Machine Annotated Database of Canonical Hungarian Poetry</title>
</titleInfo>
<name type="personal">
<namePart type="given">Péter</namePart>
<namePart type="family">Horváth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Péter</namePart>
<namePart type="family">Kundráth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Balázs</namePart>
<namePart type="family">Indig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zsófia</namePart>
<namePart type="family">Fellegi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eszter</namePart>
<namePart type="family">Szlávich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tímea</namePart>
<namePart type="given">Borbála</namePart>
<namePart type="family">Bajzát</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zsófia</namePart>
<namePart type="family">Sárközi-Lindner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bence</namePart>
<namePart type="family">Vida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aslihan</namePart>
<namePart type="family">Karabulut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mária</namePart>
<namePart type="family">Timári</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gábor</namePart>
<namePart type="family">Palkó</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>ELTE Poetry Corpus is a database that stores canonical Hungarian poetry with automatically generated annotations of the poems’ structural units, grammatical features and sound devices, i.e. rhyme patterns, rhyme pairs, rhythm, alliterations and the main phonological features of words. The corpus has an open access online query tool with several search functions. The paper presents the main stages of the annotation process and the tools used for each stage. The TEI XML format of the different versions of the corpus, each of which contains an increasing number of annotation layers, is presented as well. We have also specified our own XML format for the corpus, slightly different from TEI, in order to make it easier and faster to execute queries on the corpus. We discuss the results of a manual evaluation of the quality of automatic annotation of rhythm, as well as the results of an automatic evaluation of different rule sets used for the automatic annotation of rhyme patterns. Finally, the paper gives an overview of the main functions of the online query tool developed for the corpus.</abstract>
<identifier type="citekey">horvath-etal-2022-elte</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.372</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>3471</start>
<end>3478</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ELTE Poetry Corpus: A Machine Annotated Database of Canonical Hungarian Poetry
%A Horváth, Péter
%A Kundráth, Péter
%A Indig, Balázs
%A Fellegi, Zsófia
%A Szlávich, Eszter
%A Bajzát, Tímea Borbála
%A Sárközi-Lindner, Zsófia
%A Vida, Bence
%A Karabulut, Aslihan
%A Timári, Mária
%A Palkó, Gábor
%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 horvath-etal-2022-elte
%X ELTE Poetry Corpus is a database that stores canonical Hungarian poetry with automatically generated annotations of the poems’ structural units, grammatical features and sound devices, i.e. rhyme patterns, rhyme pairs, rhythm, alliterations and the main phonological features of words. The corpus has an open access online query tool with several search functions. The paper presents the main stages of the annotation process and the tools used for each stage. The TEI XML format of the different versions of the corpus, each of which contains an increasing number of annotation layers, is presented as well. We have also specified our own XML format for the corpus, slightly different from TEI, in order to make it easier and faster to execute queries on the corpus. We discuss the results of a manual evaluation of the quality of automatic annotation of rhythm, as well as the results of an automatic evaluation of different rule sets used for the automatic annotation of rhyme patterns. Finally, the paper gives an overview of the main functions of the online query tool developed for the corpus.
%U https://aclanthology.org/2022.lrec-1.372
%P 3471-3478
Markdown (Informal)
[ELTE Poetry Corpus: A Machine Annotated Database of Canonical Hungarian Poetry](https://aclanthology.org/2022.lrec-1.372) (Horváth et al., LREC 2022)
ACL
- Péter Horváth, Péter Kundráth, Balázs Indig, Zsófia Fellegi, Eszter Szlávich, Tímea Borbála Bajzát, Zsófia Sárközi-Lindner, Bence Vida, Aslihan Karabulut, Mária Timári, and Gábor Palkó. 2022. ELTE Poetry Corpus: A Machine Annotated Database of Canonical Hungarian Poetry. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 3471–3478, Marseille, France. European Language Resources Association.