@inproceedings{aguero-torales-etal-2021-logistical,
title = "On the logistical difficulties and findings of Jopara Sentiment Analysis",
author = {Ag{\"u}ero-Torales, Marvin and
Vilares, David and
L{\'o}pez-Herrera, Antonio},
booktitle = "Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.calcs-1.12",
doi = "10.18653/v1/2021.calcs-1.12",
pages = "95--102",
abstract = "This paper addresses the problem of sentiment analysis for Jopara, a code-switching language between Guarani and Spanish. We first collect a corpus of Guarani-dominant tweets and discuss on the difficulties of finding quality data for even relatively easy-to-annotate tasks, such as sentiment analysis. Then, we train a set of neural models, including pre-trained language models, and explore whether they perform better than traditional machine learning ones in this low-resource setup. Transformer architectures obtain the best results, despite not considering Guarani during pre-training, but traditional machine learning models perform close due to the low-resource nature of the problem.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aguero-torales-etal-2021-logistical">
<titleInfo>
<title>On the logistical difficulties and findings of Jopara Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marvin</namePart>
<namePart type="family">Agüero-Torales</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Vilares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">López-Herrera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper addresses the problem of sentiment analysis for Jopara, a code-switching language between Guarani and Spanish. We first collect a corpus of Guarani-dominant tweets and discuss on the difficulties of finding quality data for even relatively easy-to-annotate tasks, such as sentiment analysis. Then, we train a set of neural models, including pre-trained language models, and explore whether they perform better than traditional machine learning ones in this low-resource setup. Transformer architectures obtain the best results, despite not considering Guarani during pre-training, but traditional machine learning models perform close due to the low-resource nature of the problem.</abstract>
<identifier type="citekey">aguero-torales-etal-2021-logistical</identifier>
<identifier type="doi">10.18653/v1/2021.calcs-1.12</identifier>
<location>
<url>https://aclanthology.org/2021.calcs-1.12</url>
</location>
<part>
<date>2021-jun</date>
<extent unit="page">
<start>95</start>
<end>102</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the logistical difficulties and findings of Jopara Sentiment Analysis
%A Agüero-Torales, Marvin
%A Vilares, David
%A López-Herrera, Antonio
%S Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching
%D 2021
%8 jun
%I Association for Computational Linguistics
%C Online
%F aguero-torales-etal-2021-logistical
%X This paper addresses the problem of sentiment analysis for Jopara, a code-switching language between Guarani and Spanish. We first collect a corpus of Guarani-dominant tweets and discuss on the difficulties of finding quality data for even relatively easy-to-annotate tasks, such as sentiment analysis. Then, we train a set of neural models, including pre-trained language models, and explore whether they perform better than traditional machine learning ones in this low-resource setup. Transformer architectures obtain the best results, despite not considering Guarani during pre-training, but traditional machine learning models perform close due to the low-resource nature of the problem.
%R 10.18653/v1/2021.calcs-1.12
%U https://aclanthology.org/2021.calcs-1.12
%U https://doi.org/10.18653/v1/2021.calcs-1.12
%P 95-102
Markdown (Informal)
[On the logistical difficulties and findings of Jopara Sentiment Analysis](https://aclanthology.org/2021.calcs-1.12) (Agüero-Torales et al., CALCS 2021)
ACL