@inproceedings{beniamine-etal-2024-eesthetic-paralex,
title = "Eesthetic: A Paralex Lexicon of {E}stonian Paradigms",
author = "Beniamine, Sacha and
Aigro, Mari and
Baerman, Matthew and
Bouton, Jules and
Copot, Maria",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.491",
pages = "5526--5537",
abstract = "We introduce Eesthetic, a comprehensive Estonian noun and verb lexicon sourced from the Ekilex database. It documents 5475 nouns inflecting for 28 paradigm cells and 5076 verbs inflecting for 51 cells, and comprises a total of 452885 inflected forms. Our openly accessible machine-readable dataset adheres to the Paralex standard. It comprises CSV tables linked by formal relationships. Metadata in JSON format, following the Frictionless standard, provides detailed descriptions of the tables and dataset. The lexicon offers extensive linguistic annotations, including orthographic forms, automatically transcribed phonemic transcriptions, non-canonical morphological phenomena such as overabundance and defectiveness, rich mapping of the paradigm cells and feature-values to other notation schemes, a decomposition of phonemes in distinctive features, and annotation of inflection classes. It is suited for both monolingual and comparative research, enabling qualitative and quantitative analysis. This paper outlines the creation process, rationale, and resulting structure, along with our set of rules for automatic orthography-to-phonemic transcription conversion.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="beniamine-etal-2024-eesthetic-paralex">
<titleInfo>
<title>Eesthetic: A Paralex Lexicon of Estonian Paradigms</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sacha</namePart>
<namePart type="family">Beniamine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mari</namePart>
<namePart type="family">Aigro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Baerman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jules</namePart>
<namePart type="family">Bouton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Copot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce Eesthetic, a comprehensive Estonian noun and verb lexicon sourced from the Ekilex database. It documents 5475 nouns inflecting for 28 paradigm cells and 5076 verbs inflecting for 51 cells, and comprises a total of 452885 inflected forms. Our openly accessible machine-readable dataset adheres to the Paralex standard. It comprises CSV tables linked by formal relationships. Metadata in JSON format, following the Frictionless standard, provides detailed descriptions of the tables and dataset. The lexicon offers extensive linguistic annotations, including orthographic forms, automatically transcribed phonemic transcriptions, non-canonical morphological phenomena such as overabundance and defectiveness, rich mapping of the paradigm cells and feature-values to other notation schemes, a decomposition of phonemes in distinctive features, and annotation of inflection classes. It is suited for both monolingual and comparative research, enabling qualitative and quantitative analysis. This paper outlines the creation process, rationale, and resulting structure, along with our set of rules for automatic orthography-to-phonemic transcription conversion.</abstract>
<identifier type="citekey">beniamine-etal-2024-eesthetic-paralex</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.491</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>5526</start>
<end>5537</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Eesthetic: A Paralex Lexicon of Estonian Paradigms
%A Beniamine, Sacha
%A Aigro, Mari
%A Baerman, Matthew
%A Bouton, Jules
%A Copot, Maria
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F beniamine-etal-2024-eesthetic-paralex
%X We introduce Eesthetic, a comprehensive Estonian noun and verb lexicon sourced from the Ekilex database. It documents 5475 nouns inflecting for 28 paradigm cells and 5076 verbs inflecting for 51 cells, and comprises a total of 452885 inflected forms. Our openly accessible machine-readable dataset adheres to the Paralex standard. It comprises CSV tables linked by formal relationships. Metadata in JSON format, following the Frictionless standard, provides detailed descriptions of the tables and dataset. The lexicon offers extensive linguistic annotations, including orthographic forms, automatically transcribed phonemic transcriptions, non-canonical morphological phenomena such as overabundance and defectiveness, rich mapping of the paradigm cells and feature-values to other notation schemes, a decomposition of phonemes in distinctive features, and annotation of inflection classes. It is suited for both monolingual and comparative research, enabling qualitative and quantitative analysis. This paper outlines the creation process, rationale, and resulting structure, along with our set of rules for automatic orthography-to-phonemic transcription conversion.
%U https://aclanthology.org/2024.lrec-main.491
%P 5526-5537
Markdown (Informal)
[Eesthetic: A Paralex Lexicon of Estonian Paradigms](https://aclanthology.org/2024.lrec-main.491) (Beniamine et al., LREC-COLING 2024)
ACL
- Sacha Beniamine, Mari Aigro, Matthew Baerman, Jules Bouton, and Maria Copot. 2024. Eesthetic: A Paralex Lexicon of Estonian Paradigms. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5526–5537, Torino, Italia. ELRA and ICCL.