@inproceedings{zanotto-etal-2024-grit-dataset,
title = "{GRIT}: A Dataset of Group Reference Recognition in {I}talian",
author = "Zanotto, Sergio E. and
Yu, Qi and
Butt, Miriam and
Frassinelli, Diego",
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.701",
pages = "7963--7970",
abstract = "For the analysis of political discourse a reliable identification of group references, i.e., linguistic components that refer to individuals or groups of people, is useful. However, the task of automatically recognizing group references has not yet gained much attention within NLP. To address this gap, we introduce GRIT (Group Reference for Italian), a large-scale, multi-domain manually annotated dataset for group reference recognition in Italian. GRIT represents a new resource for automatic and generalizable recognition of group references. With this dataset, we aim to establish group reference recognition as a valid classification task, which extends the domain of Named Entity Recognition by expanding its focus to literal and figurative mentions of social groups. We verify the potential of achieving automated group reference recognition for Italian through an experiment employing a fine-tuned BERT model. Our experimental results substantiate the validity of the task, implying a huge potential for applying automated systems to multiple fields of analysis, such as political text or social media analysis.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zanotto-etal-2024-grit-dataset">
<titleInfo>
<title>GRIT: A Dataset of Group Reference Recognition in Italian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sergio</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Zanotto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miriam</namePart>
<namePart type="family">Butt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Frassinelli</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>For the analysis of political discourse a reliable identification of group references, i.e., linguistic components that refer to individuals or groups of people, is useful. However, the task of automatically recognizing group references has not yet gained much attention within NLP. To address this gap, we introduce GRIT (Group Reference for Italian), a large-scale, multi-domain manually annotated dataset for group reference recognition in Italian. GRIT represents a new resource for automatic and generalizable recognition of group references. With this dataset, we aim to establish group reference recognition as a valid classification task, which extends the domain of Named Entity Recognition by expanding its focus to literal and figurative mentions of social groups. We verify the potential of achieving automated group reference recognition for Italian through an experiment employing a fine-tuned BERT model. Our experimental results substantiate the validity of the task, implying a huge potential for applying automated systems to multiple fields of analysis, such as political text or social media analysis.</abstract>
<identifier type="citekey">zanotto-etal-2024-grit-dataset</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.701</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>7963</start>
<end>7970</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GRIT: A Dataset of Group Reference Recognition in Italian
%A Zanotto, Sergio E.
%A Yu, Qi
%A Butt, Miriam
%A Frassinelli, Diego
%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 zanotto-etal-2024-grit-dataset
%X For the analysis of political discourse a reliable identification of group references, i.e., linguistic components that refer to individuals or groups of people, is useful. However, the task of automatically recognizing group references has not yet gained much attention within NLP. To address this gap, we introduce GRIT (Group Reference for Italian), a large-scale, multi-domain manually annotated dataset for group reference recognition in Italian. GRIT represents a new resource for automatic and generalizable recognition of group references. With this dataset, we aim to establish group reference recognition as a valid classification task, which extends the domain of Named Entity Recognition by expanding its focus to literal and figurative mentions of social groups. We verify the potential of achieving automated group reference recognition for Italian through an experiment employing a fine-tuned BERT model. Our experimental results substantiate the validity of the task, implying a huge potential for applying automated systems to multiple fields of analysis, such as political text or social media analysis.
%U https://aclanthology.org/2024.lrec-main.701
%P 7963-7970
Markdown (Informal)
[GRIT: A Dataset of Group Reference Recognition in Italian](https://aclanthology.org/2024.lrec-main.701) (Zanotto et al., LREC-COLING 2024)
ACL
- Sergio E. Zanotto, Qi Yu, Miriam Butt, and Diego Frassinelli. 2024. GRIT: A Dataset of Group Reference Recognition in Italian. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 7963–7970, Torino, Italia. ELRA and ICCL.