@inproceedings{de-langhe-etal-2026-echoes,
title = "Echoes of the Troubadours: A Corpus of Troubadour Poetry for Stylometric Analysis and Authorship Attribution",
author = "De Langhe, Loic and
De Clercq, Orphee and
Hoste, Veronique",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.69/",
doi = "10.63317/5kd5docuu6qb",
pages = "905--918",
abstract = "We present TrobaCor, a curated corpus of medieval troubadour poetry, which comprises 1668 unique Old Occitan texts by a large variety of authors. Clustering and stylometric experiments show that we can accurately model authorial style beyond topical content, even though formulaic or topically diverse genres remain challenging. Furthermore, we can model and detect traces of an author{'}s stylistic ``DNA'' even in short-form collaborative poetry, offering a uniquely fine-grained perspective in the field. In addition, we provide self-organizing map visualizations in order to provide an interpretable view of stylistic patterns across authors. TrobaCor is publicly released to support reproducible research in NLP and digital humanities on this low-resource historical corpus."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-langhe-etal-2026-echoes">
<titleInfo>
<title>Echoes of the Troubadours: A Corpus of Troubadour Poetry for Stylometric Analysis and Authorship Attribution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Loic</namePart>
<namePart type="family">De Langhe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orphee</namePart>
<namePart type="family">De Clercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present TrobaCor, a curated corpus of medieval troubadour poetry, which comprises 1668 unique Old Occitan texts by a large variety of authors. Clustering and stylometric experiments show that we can accurately model authorial style beyond topical content, even though formulaic or topically diverse genres remain challenging. Furthermore, we can model and detect traces of an author’s stylistic “DNA” even in short-form collaborative poetry, offering a uniquely fine-grained perspective in the field. In addition, we provide self-organizing map visualizations in order to provide an interpretable view of stylistic patterns across authors. TrobaCor is publicly released to support reproducible research in NLP and digital humanities on this low-resource historical corpus.</abstract>
<identifier type="citekey">de-langhe-etal-2026-echoes</identifier>
<identifier type="doi">10.63317/5kd5docuu6qb</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.69/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>905</start>
<end>918</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Echoes of the Troubadours: A Corpus of Troubadour Poetry for Stylometric Analysis and Authorship Attribution
%A De Langhe, Loic
%A De Clercq, Orphee
%A Hoste, Veronique
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F de-langhe-etal-2026-echoes
%X We present TrobaCor, a curated corpus of medieval troubadour poetry, which comprises 1668 unique Old Occitan texts by a large variety of authors. Clustering and stylometric experiments show that we can accurately model authorial style beyond topical content, even though formulaic or topically diverse genres remain challenging. Furthermore, we can model and detect traces of an author’s stylistic “DNA” even in short-form collaborative poetry, offering a uniquely fine-grained perspective in the field. In addition, we provide self-organizing map visualizations in order to provide an interpretable view of stylistic patterns across authors. TrobaCor is publicly released to support reproducible research in NLP and digital humanities on this low-resource historical corpus.
%R 10.63317/5kd5docuu6qb
%U https://aclanthology.org/2026.lrec-1.69/
%U https://doi.org/10.63317/5kd5docuu6qb
%P 905-918
Markdown (Informal)
[Echoes of the Troubadours: A Corpus of Troubadour Poetry for Stylometric Analysis and Authorship Attribution](https://aclanthology.org/2026.lrec-1.69/) (De Langhe et al., LREC 2026)
ACL