@inproceedings{martinelli-etal-2024-exploring,
title = "Exploring Neural Topic Modeling on a Classical {L}atin Corpus",
author = "Martinelli, Ginevra and
Impiccich{\'e}, Paola and
Fersini, Elisabetta and
Mambrini, Francesco and
Passarotti, Marco",
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.606",
pages = "6929--6934",
abstract = "The large availability of processable textual resources for Classical Latin has made it possible to study Latin literature through methods and tools that support distant reading. This paper describes a number of experiments carried out to test the possibility of investigating the thematic distribution of the Classical Latin corpus Opera Latina by means of topic modeling. For this purpose, we train, optimize and compare two neural models, Product-of-Experts LDA (ProdLDA) and Embedded Topic Model (ETM), opportunely revised to deal with the textual data from a Classical Latin corpus, to evaluate which one performs better both on the basis of topic diversity and topic coherence metrics, and from a human judgment point of view. Our results show that the topics extracted by neural models are coherent and interpretable and that they are significant from the perspective of a Latin scholar. The source code of the proposed model is available at https://github.com/MIND-Lab/LatinProdLDA.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="martinelli-etal-2024-exploring">
<titleInfo>
<title>Exploring Neural Topic Modeling on a Classical Latin Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ginevra</namePart>
<namePart type="family">Martinelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Impicciché</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisabetta</namePart>
<namePart type="family">Fersini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesco</namePart>
<namePart type="family">Mambrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Passarotti</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>The large availability of processable textual resources for Classical Latin has made it possible to study Latin literature through methods and tools that support distant reading. This paper describes a number of experiments carried out to test the possibility of investigating the thematic distribution of the Classical Latin corpus Opera Latina by means of topic modeling. For this purpose, we train, optimize and compare two neural models, Product-of-Experts LDA (ProdLDA) and Embedded Topic Model (ETM), opportunely revised to deal with the textual data from a Classical Latin corpus, to evaluate which one performs better both on the basis of topic diversity and topic coherence metrics, and from a human judgment point of view. Our results show that the topics extracted by neural models are coherent and interpretable and that they are significant from the perspective of a Latin scholar. The source code of the proposed model is available at https://github.com/MIND-Lab/LatinProdLDA.</abstract>
<identifier type="citekey">martinelli-etal-2024-exploring</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.606</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>6929</start>
<end>6934</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Neural Topic Modeling on a Classical Latin Corpus
%A Martinelli, Ginevra
%A Impicciché, Paola
%A Fersini, Elisabetta
%A Mambrini, Francesco
%A Passarotti, Marco
%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 martinelli-etal-2024-exploring
%X The large availability of processable textual resources for Classical Latin has made it possible to study Latin literature through methods and tools that support distant reading. This paper describes a number of experiments carried out to test the possibility of investigating the thematic distribution of the Classical Latin corpus Opera Latina by means of topic modeling. For this purpose, we train, optimize and compare two neural models, Product-of-Experts LDA (ProdLDA) and Embedded Topic Model (ETM), opportunely revised to deal with the textual data from a Classical Latin corpus, to evaluate which one performs better both on the basis of topic diversity and topic coherence metrics, and from a human judgment point of view. Our results show that the topics extracted by neural models are coherent and interpretable and that they are significant from the perspective of a Latin scholar. The source code of the proposed model is available at https://github.com/MIND-Lab/LatinProdLDA.
%U https://aclanthology.org/2024.lrec-main.606
%P 6929-6934
Markdown (Informal)
[Exploring Neural Topic Modeling on a Classical Latin Corpus](https://aclanthology.org/2024.lrec-main.606) (Martinelli et al., LREC-COLING 2024)
ACL
- Ginevra Martinelli, Paola Impicciché, Elisabetta Fersini, Francesco Mambrini, and Marco Passarotti. 2024. Exploring Neural Topic Modeling on a Classical Latin Corpus. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 6929–6934, Torino, Italia. ELRA and ICCL.