@inproceedings{agnoloni-etal-2022-clustering,
title = "Clustering Similar Amendments at the {I}talian Senate",
author = "Agnoloni, Tommaso and
Marchetti, Carlo and
Battistoni, Roberto and
Briotti, Giuseppe",
editor = "Fi{\v{s}}er, Darja and
Eskevich, Maria and
Lenardi{\v{c}}, Jakob and
de Jong, Franciska",
booktitle = "Proceedings of the Workshop ParlaCLARIN III within the 13th Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.parlaclarin-1.7",
pages = "39--46",
abstract = "In this paper we describe an experiment for the application of text clustering techniques to dossiers of amendments to proposed legislation discussed in the Italian Senate. The aim is to assist the Senate staff in the detection of groups of amendments similar in their textual formulation in order to schedule their simultaneous voting. Experiments show that the exploitation (extraction, annotation and normalization) of domain features is crucial to improve the clustering performance in many problematic cases not properly dealt with by standard approaches. The similarity engine was implemented and integrated as an experimental feature in the internal application used for the management of amendments in the Senate Assembly and Committees. Thanks to the Open Data strategy pursued by the Senate for several years, all documents and data produced by the institution are publicly available for reuse in open formats.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="agnoloni-etal-2022-clustering">
<titleInfo>
<title>Clustering Similar Amendments at the Italian Senate</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tommaso</namePart>
<namePart type="family">Agnoloni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlo</namePart>
<namePart type="family">Marchetti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Battistoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Briotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop ParlaCLARIN III within the 13th Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Darja</namePart>
<namePart type="family">Fišer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Eskevich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jakob</namePart>
<namePart type="family">Lenardič</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Franciska</namePart>
<namePart type="family">de Jong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we describe an experiment for the application of text clustering techniques to dossiers of amendments to proposed legislation discussed in the Italian Senate. The aim is to assist the Senate staff in the detection of groups of amendments similar in their textual formulation in order to schedule their simultaneous voting. Experiments show that the exploitation (extraction, annotation and normalization) of domain features is crucial to improve the clustering performance in many problematic cases not properly dealt with by standard approaches. The similarity engine was implemented and integrated as an experimental feature in the internal application used for the management of amendments in the Senate Assembly and Committees. Thanks to the Open Data strategy pursued by the Senate for several years, all documents and data produced by the institution are publicly available for reuse in open formats.</abstract>
<identifier type="citekey">agnoloni-etal-2022-clustering</identifier>
<location>
<url>https://aclanthology.org/2022.parlaclarin-1.7</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>39</start>
<end>46</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Clustering Similar Amendments at the Italian Senate
%A Agnoloni, Tommaso
%A Marchetti, Carlo
%A Battistoni, Roberto
%A Briotti, Giuseppe
%Y Fišer, Darja
%Y Eskevich, Maria
%Y Lenardič, Jakob
%Y de Jong, Franciska
%S Proceedings of the Workshop ParlaCLARIN III within the 13th Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F agnoloni-etal-2022-clustering
%X In this paper we describe an experiment for the application of text clustering techniques to dossiers of amendments to proposed legislation discussed in the Italian Senate. The aim is to assist the Senate staff in the detection of groups of amendments similar in their textual formulation in order to schedule their simultaneous voting. Experiments show that the exploitation (extraction, annotation and normalization) of domain features is crucial to improve the clustering performance in many problematic cases not properly dealt with by standard approaches. The similarity engine was implemented and integrated as an experimental feature in the internal application used for the management of amendments in the Senate Assembly and Committees. Thanks to the Open Data strategy pursued by the Senate for several years, all documents and data produced by the institution are publicly available for reuse in open formats.
%U https://aclanthology.org/2022.parlaclarin-1.7
%P 39-46
Markdown (Informal)
[Clustering Similar Amendments at the Italian Senate](https://aclanthology.org/2022.parlaclarin-1.7) (Agnoloni et al., ParlaCLARIN 2022)
ACL
- Tommaso Agnoloni, Carlo Marchetti, Roberto Battistoni, and Giuseppe Briotti. 2022. Clustering Similar Amendments at the Italian Senate. In Proceedings of the Workshop ParlaCLARIN III within the 13th Language Resources and Evaluation Conference, pages 39–46, Marseille, France. European Language Resources Association.