@inproceedings{paccosi-palmero-aprosio-2022-kind,
title = "{KIND}: an {I}talian Multi-Domain Dataset for Named Entity Recognition",
author = "Paccosi, Teresa and
Palmero Aprosio, Alessio",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.52",
pages = "501--507",
abstract = "In this paper we present KIND, an Italian dataset for Named-entity recognition. It contains more than one million tokens with annotation covering three classes: person, location, and organization. The dataset (around 600K tokens) mostly contains manual gold annotations in three different domains (news, literature, and political discourses) and a semi-automatically annotated part. The multi-domain feature is the main strength of the present work, offering a resource which covers different styles and language uses, as well as the largest Italian NER dataset with manual gold annotations. It represents an important resource for the training of NER systems in Italian. Texts and annotations are freely downloadable from the Github repository.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="paccosi-palmero-aprosio-2022-kind">
<titleInfo>
<title>KIND: an Italian Multi-Domain Dataset for Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Teresa</namePart>
<namePart type="family">Paccosi</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>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</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 present KIND, an Italian dataset for Named-entity recognition. It contains more than one million tokens with annotation covering three classes: person, location, and organization. The dataset (around 600K tokens) mostly contains manual gold annotations in three different domains (news, literature, and political discourses) and a semi-automatically annotated part. The multi-domain feature is the main strength of the present work, offering a resource which covers different styles and language uses, as well as the largest Italian NER dataset with manual gold annotations. It represents an important resource for the training of NER systems in Italian. Texts and annotations are freely downloadable from the Github repository.</abstract>
<identifier type="citekey">paccosi-palmero-aprosio-2022-kind</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.52</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>501</start>
<end>507</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KIND: an Italian Multi-Domain Dataset for Named Entity Recognition
%A Paccosi, Teresa
%A Palmero Aprosio, Alessio
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F paccosi-palmero-aprosio-2022-kind
%X In this paper we present KIND, an Italian dataset for Named-entity recognition. It contains more than one million tokens with annotation covering three classes: person, location, and organization. The dataset (around 600K tokens) mostly contains manual gold annotations in three different domains (news, literature, and political discourses) and a semi-automatically annotated part. The multi-domain feature is the main strength of the present work, offering a resource which covers different styles and language uses, as well as the largest Italian NER dataset with manual gold annotations. It represents an important resource for the training of NER systems in Italian. Texts and annotations are freely downloadable from the Github repository.
%U https://aclanthology.org/2022.lrec-1.52
%P 501-507
Markdown (Informal)
[KIND: an Italian Multi-Domain Dataset for Named Entity Recognition](https://aclanthology.org/2022.lrec-1.52) (Paccosi & Palmero Aprosio, LREC 2022)
ACL