@inproceedings{basile-etal-2024-pyrater-python,
title = "{P}y{R}ater: A Python Toolkit for Annotation Analysis",
author = "Basile, Angelo and
Franco-Salvador, Marc and
Rosso, Paolo",
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.1169",
pages = "13356--13362",
abstract = "We introduce PyRater, an open-source Python toolkit designed for analysing corpora annotations. When creating new annotated language resources, probabilistic models of annotation are the state-of-the-art solution for identifying the best annotators, retrieving the gold standard, and more generally separating annotation signal from noise. PyRater offers a unified interface for several such models and includes an API for the addition of new ones. Additionally, the toolkit has built-in functions to read datasets with multiple annotations and plot the analysis outcomes. In this work, we also demonstrate a novel application of PyRater to zero-shot classifiers, where it effectively selects the best-performing prompt. We make PyRater available to the research community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="basile-etal-2024-pyrater-python">
<titleInfo>
<title>PyRater: A Python Toolkit for Annotation Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Angelo</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Franco-Salvador</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paolo</namePart>
<namePart type="family">Rosso</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>We introduce PyRater, an open-source Python toolkit designed for analysing corpora annotations. When creating new annotated language resources, probabilistic models of annotation are the state-of-the-art solution for identifying the best annotators, retrieving the gold standard, and more generally separating annotation signal from noise. PyRater offers a unified interface for several such models and includes an API for the addition of new ones. Additionally, the toolkit has built-in functions to read datasets with multiple annotations and plot the analysis outcomes. In this work, we also demonstrate a novel application of PyRater to zero-shot classifiers, where it effectively selects the best-performing prompt. We make PyRater available to the research community.</abstract>
<identifier type="citekey">basile-etal-2024-pyrater-python</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1169</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>13356</start>
<end>13362</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PyRater: A Python Toolkit for Annotation Analysis
%A Basile, Angelo
%A Franco-Salvador, Marc
%A Rosso, Paolo
%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 basile-etal-2024-pyrater-python
%X We introduce PyRater, an open-source Python toolkit designed for analysing corpora annotations. When creating new annotated language resources, probabilistic models of annotation are the state-of-the-art solution for identifying the best annotators, retrieving the gold standard, and more generally separating annotation signal from noise. PyRater offers a unified interface for several such models and includes an API for the addition of new ones. Additionally, the toolkit has built-in functions to read datasets with multiple annotations and plot the analysis outcomes. In this work, we also demonstrate a novel application of PyRater to zero-shot classifiers, where it effectively selects the best-performing prompt. We make PyRater available to the research community.
%U https://aclanthology.org/2024.lrec-main.1169
%P 13356-13362
Markdown (Informal)
[PyRater: A Python Toolkit for Annotation Analysis](https://aclanthology.org/2024.lrec-main.1169) (Basile et al., LREC-COLING 2024)
ACL
- Angelo Basile, Marc Franco-Salvador, and Paolo Rosso. 2024. PyRater: A Python Toolkit for Annotation Analysis. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 13356–13362, Torino, Italia. ELRA and ICCL.