@inproceedings{calderaro-monti-2026-bolu,
title = "A {B}olu: A Structured Dataset for the Computational Analysis of {S}ardinian Improvisational Poetry",
author = "Calderaro, Silvio and
Monti, Johanna",
editor = "Anastasopoulos, Antonis and
Markantonatou, Stella and
Ralli, Angela and
Zampieri, Marcos and
Bompolas, Stavros and
Stamou, Vivian",
booktitle = "Proceedings of the First Workshop on Dialects in {NLP} {---} A Resource Perspective",
month = may,
year = "2026",
address = "Palma de Mallorca",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.dialres-1.1/",
doi = "10.63317/3d9ufzotw55s",
pages = "1--11",
abstract = "The growing interest of Natural Language Processing (NLP) in minority languages has not yet bridged the gap in the preservation of oral linguistic heritage. In particular, extemporaneous poetry {---} a performative genre based on real-time improvisation, metrical-rhetorical competence {---} remains a largely unexplored area of computational linguistics. This methodological gap necessitates the creation of specific resources to document and analyse the structures of improvised poetry. This is the context in which A Bolu was created, the first structured corpus of extemporaneous poetry dedicated to cantada logudorese, a variant of the Sardinian language. The dataset comprises 2,835 stanzas for a total of 141,321 tokens. The study presents the architecture of the corpus and applies a multidimensional analysis combining descriptive statistical indices and computational linguistics techniques to map the characteristics of the poetic text. The results indicate that the production of Sardinian extemporaneous poets is characterised by recurring patterns that support Parry and Lord{'}s theory of formulaicity. This evidence not only provides a new key to understanding oral creativity, but also offers a significant contribution to the development of NLP tools that are more inclusive and sensitive to the specificities of less widely spoken languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="calderaro-monti-2026-bolu">
<titleInfo>
<title>A Bolu: A Structured Dataset for the Computational Analysis of Sardinian Improvisational Poetry</title>
</titleInfo>
<name type="personal">
<namePart type="given">Silvio</namePart>
<namePart type="family">Calderaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Monti</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 First Workshop on Dialects in NLP — A Resource Perspective</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antonis</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stella</namePart>
<namePart type="family">Markantonatou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Ralli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stavros</namePart>
<namePart type="family">Bompolas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivian</namePart>
<namePart type="family">Stamou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Palma de Mallorca</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The growing interest of Natural Language Processing (NLP) in minority languages has not yet bridged the gap in the preservation of oral linguistic heritage. In particular, extemporaneous poetry — a performative genre based on real-time improvisation, metrical-rhetorical competence — remains a largely unexplored area of computational linguistics. This methodological gap necessitates the creation of specific resources to document and analyse the structures of improvised poetry. This is the context in which A Bolu was created, the first structured corpus of extemporaneous poetry dedicated to cantada logudorese, a variant of the Sardinian language. The dataset comprises 2,835 stanzas for a total of 141,321 tokens. The study presents the architecture of the corpus and applies a multidimensional analysis combining descriptive statistical indices and computational linguistics techniques to map the characteristics of the poetic text. The results indicate that the production of Sardinian extemporaneous poets is characterised by recurring patterns that support Parry and Lord’s theory of formulaicity. This evidence not only provides a new key to understanding oral creativity, but also offers a significant contribution to the development of NLP tools that are more inclusive and sensitive to the specificities of less widely spoken languages.</abstract>
<identifier type="citekey">calderaro-monti-2026-bolu</identifier>
<identifier type="doi">10.63317/3d9ufzotw55s</identifier>
<location>
<url>https://aclanthology.org/2026.dialres-1.1/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1</start>
<end>11</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Bolu: A Structured Dataset for the Computational Analysis of Sardinian Improvisational Poetry
%A Calderaro, Silvio
%A Monti, Johanna
%Y Anastasopoulos, Antonis
%Y Markantonatou, Stella
%Y Ralli, Angela
%Y Zampieri, Marcos
%Y Bompolas, Stavros
%Y Stamou, Vivian
%S Proceedings of the First Workshop on Dialects in NLP — A Resource Perspective
%D 2026
%8 May
%I Association for Computational Linguistics
%C Palma de Mallorca
%F calderaro-monti-2026-bolu
%X The growing interest of Natural Language Processing (NLP) in minority languages has not yet bridged the gap in the preservation of oral linguistic heritage. In particular, extemporaneous poetry — a performative genre based on real-time improvisation, metrical-rhetorical competence — remains a largely unexplored area of computational linguistics. This methodological gap necessitates the creation of specific resources to document and analyse the structures of improvised poetry. This is the context in which A Bolu was created, the first structured corpus of extemporaneous poetry dedicated to cantada logudorese, a variant of the Sardinian language. The dataset comprises 2,835 stanzas for a total of 141,321 tokens. The study presents the architecture of the corpus and applies a multidimensional analysis combining descriptive statistical indices and computational linguistics techniques to map the characteristics of the poetic text. The results indicate that the production of Sardinian extemporaneous poets is characterised by recurring patterns that support Parry and Lord’s theory of formulaicity. This evidence not only provides a new key to understanding oral creativity, but also offers a significant contribution to the development of NLP tools that are more inclusive and sensitive to the specificities of less widely spoken languages.
%R 10.63317/3d9ufzotw55s
%U https://aclanthology.org/2026.dialres-1.1/
%U https://doi.org/10.63317/3d9ufzotw55s
%P 1-11
Markdown (Informal)
[A Bolu: A Structured Dataset for the Computational Analysis of Sardinian Improvisational Poetry](https://aclanthology.org/2026.dialres-1.1/) (Calderaro & Monti, DialRes 2026)
ACL