@inproceedings{tepei-bloem-2024-automatic-animacy,
title = "Automatic {A}nimacy Classification for {R}omanian Nouns",
author = "Tepei, Maria and
Bloem, Jelke",
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.163",
pages = "1825--1831",
abstract = "We introduce the first Romanian animacy classifier, specifically a type-based binary classifier of Romanian nouns into the classes human/non-human, using pre-trained word embeddings and animacy information derived from Romanian WordNet. By obtaining a seed set of labeled nouns and their embeddings, we are able to train classifiers that generalize to unseen nouns. We compare three different architectures and observe good performance on classifying word types. In addition, we manually annotate a small corpus for animacy to perform a token-based evaluation of Romanian animacy classification in a naturalistic setting, which reveals limitations of the type-based classification approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tepei-bloem-2024-automatic-animacy">
<titleInfo>
<title>Automatic Animacy Classification for Romanian Nouns</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Tepei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jelke</namePart>
<namePart type="family">Bloem</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 the first Romanian animacy classifier, specifically a type-based binary classifier of Romanian nouns into the classes human/non-human, using pre-trained word embeddings and animacy information derived from Romanian WordNet. By obtaining a seed set of labeled nouns and their embeddings, we are able to train classifiers that generalize to unseen nouns. We compare three different architectures and observe good performance on classifying word types. In addition, we manually annotate a small corpus for animacy to perform a token-based evaluation of Romanian animacy classification in a naturalistic setting, which reveals limitations of the type-based classification approach.</abstract>
<identifier type="citekey">tepei-bloem-2024-automatic-animacy</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.163</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>1825</start>
<end>1831</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Animacy Classification for Romanian Nouns
%A Tepei, Maria
%A Bloem, Jelke
%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 tepei-bloem-2024-automatic-animacy
%X We introduce the first Romanian animacy classifier, specifically a type-based binary classifier of Romanian nouns into the classes human/non-human, using pre-trained word embeddings and animacy information derived from Romanian WordNet. By obtaining a seed set of labeled nouns and their embeddings, we are able to train classifiers that generalize to unseen nouns. We compare three different architectures and observe good performance on classifying word types. In addition, we manually annotate a small corpus for animacy to perform a token-based evaluation of Romanian animacy classification in a naturalistic setting, which reveals limitations of the type-based classification approach.
%U https://aclanthology.org/2024.lrec-main.163
%P 1825-1831
Markdown (Informal)
[Automatic Animacy Classification for Romanian Nouns](https://aclanthology.org/2024.lrec-main.163) (Tepei & Bloem, LREC-COLING 2024)
ACL
- Maria Tepei and Jelke Bloem. 2024. Automatic Animacy Classification for Romanian Nouns. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 1825–1831, Torino, Italia. ELRA and ICCL.