@inproceedings{frasnelli-palmero-aprosio-2024-theres,
title = "There{'}s Something New about the {I}talian Parliament: The {IPSA} Corpus",
author = "Frasnelli, Valentino and
Palmero Aprosio, Alessio",
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.1394",
pages = "16037--16046",
abstract = "Parliamentary debates constitute a substantial and somewhat underutilized reservoir of publicly available written content. Despite their potential, the Italian parliamentary documents remain largely unexplored and most importantly inaccessible in their original paper-based form. In this paper we attempt to transform these valuable historical documents into IPSA, a digitally readable structured corpus containing speeches, reports of the Standing Committees, and law proposals spanning 175 years of Italian history, from the issuing of the Statuto Albertino in 1848, up to the present day. At first, the PDF documents, available on the official websites of Senato della Repubblica and Camera dei Deputati, the two chambers that form the Italian Parliament, are digitized using Optical Character Recognition (OCR) techniques. Then, the speeches are tagged with the corresponding speakers. The final dataset is released both in textual and structured format.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="frasnelli-palmero-aprosio-2024-theres">
<titleInfo>
<title>There’s Something New about the Italian Parliament: The IPSA Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Valentino</namePart>
<namePart type="family">Frasnelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessio</namePart>
<namePart type="family">Palmero Aprosio</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>Parliamentary debates constitute a substantial and somewhat underutilized reservoir of publicly available written content. Despite their potential, the Italian parliamentary documents remain largely unexplored and most importantly inaccessible in their original paper-based form. In this paper we attempt to transform these valuable historical documents into IPSA, a digitally readable structured corpus containing speeches, reports of the Standing Committees, and law proposals spanning 175 years of Italian history, from the issuing of the Statuto Albertino in 1848, up to the present day. At first, the PDF documents, available on the official websites of Senato della Repubblica and Camera dei Deputati, the two chambers that form the Italian Parliament, are digitized using Optical Character Recognition (OCR) techniques. Then, the speeches are tagged with the corresponding speakers. The final dataset is released both in textual and structured format.</abstract>
<identifier type="citekey">frasnelli-palmero-aprosio-2024-theres</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1394</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>16037</start>
<end>16046</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T There’s Something New about the Italian Parliament: The IPSA Corpus
%A Frasnelli, Valentino
%A Palmero Aprosio, Alessio
%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 frasnelli-palmero-aprosio-2024-theres
%X Parliamentary debates constitute a substantial and somewhat underutilized reservoir of publicly available written content. Despite their potential, the Italian parliamentary documents remain largely unexplored and most importantly inaccessible in their original paper-based form. In this paper we attempt to transform these valuable historical documents into IPSA, a digitally readable structured corpus containing speeches, reports of the Standing Committees, and law proposals spanning 175 years of Italian history, from the issuing of the Statuto Albertino in 1848, up to the present day. At first, the PDF documents, available on the official websites of Senato della Repubblica and Camera dei Deputati, the two chambers that form the Italian Parliament, are digitized using Optical Character Recognition (OCR) techniques. Then, the speeches are tagged with the corresponding speakers. The final dataset is released both in textual and structured format.
%U https://aclanthology.org/2024.lrec-main.1394
%P 16037-16046
Markdown (Informal)
[There’s Something New about the Italian Parliament: The IPSA Corpus](https://aclanthology.org/2024.lrec-main.1394) (Frasnelli & Palmero Aprosio, LREC-COLING 2024)
ACL