@inproceedings{zaharia-etal-2020-upb,
title = "{UPB} at {S}em{E}val-2020 Task 9: Identifying Sentiment in Code-Mixed Social Media Texts Using Transformers and Multi-Task Learning",
author = "Zaharia, George-Eduard and
Vlad, George-Alexandru and
Cercel, Dumitru-Clementin and
Rebedea, Traian and
Chiru, Costin",
editor = "Herbelot, Aurelie and
Zhu, Xiaodan and
Palmer, Alexis and
Schneider, Nathan and
May, Jonathan and
Shutova, Ekaterina",
booktitle = "Proceedings of the Fourteenth Workshop on Semantic Evaluation",
month = dec,
year = "2020",
address = "Barcelona (online)",
publisher = "International Committee for Computational Linguistics",
url = "https://aclanthology.org/2020.semeval-1.179/",
doi = "10.18653/v1/2020.semeval-1.179",
pages = "1322--1330",
abstract = "Sentiment analysis is a process widely used in opinion mining campaigns conducted today. This phenomenon presents applications in a variety of fields, especially in collecting information related to the attitude or satisfaction of users concerning a particular subject. However, the task of managing such a process becomes noticeably more difficult when it is applied in cultures that tend to combine two languages in order to express ideas and thoughts. By interleaving words from two languages, the user can express with ease, but at the cost of making the text far less intelligible for those who are not familiar with this technique, but also for standard opinion mining algorithms. In this paper, we describe the systems developed by our team for SemEval-2020 Task 9 that aims to cover two well-known code-mixed languages: Hindi-English and Spanish-English. We intend to solve this issue by introducing a solution that takes advantage of several neural network approaches, as well as pre-trained word embeddings. Our approach (multlingual BERT) achieves promising performance on the Hindi-English task, with an average F1-score of 0.6850, registered on the competition leaderboard, ranking our team 16 out of 62 participants. For the Spanish-English task, we obtained an average F1-score of 0.7064 ranking our team 17th out of 29 participants by using another multilingual Transformer-based model, XLM-RoBERTa."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zaharia-etal-2020-upb">
<titleInfo>
<title>UPB at SemEval-2020 Task 9: Identifying Sentiment in Code-Mixed Social Media Texts Using Transformers and Multi-Task Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">George-Eduard</namePart>
<namePart type="family">Zaharia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George-Alexandru</namePart>
<namePart type="family">Vlad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dumitru-Clementin</namePart>
<namePart type="family">Cercel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Traian</namePart>
<namePart type="family">Rebedea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Costin</namePart>
<namePart type="family">Chiru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourteenth Workshop on Semantic Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aurelie</namePart>
<namePart type="family">Herbelot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">May</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona (online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sentiment analysis is a process widely used in opinion mining campaigns conducted today. This phenomenon presents applications in a variety of fields, especially in collecting information related to the attitude or satisfaction of users concerning a particular subject. However, the task of managing such a process becomes noticeably more difficult when it is applied in cultures that tend to combine two languages in order to express ideas and thoughts. By interleaving words from two languages, the user can express with ease, but at the cost of making the text far less intelligible for those who are not familiar with this technique, but also for standard opinion mining algorithms. In this paper, we describe the systems developed by our team for SemEval-2020 Task 9 that aims to cover two well-known code-mixed languages: Hindi-English and Spanish-English. We intend to solve this issue by introducing a solution that takes advantage of several neural network approaches, as well as pre-trained word embeddings. Our approach (multlingual BERT) achieves promising performance on the Hindi-English task, with an average F1-score of 0.6850, registered on the competition leaderboard, ranking our team 16 out of 62 participants. For the Spanish-English task, we obtained an average F1-score of 0.7064 ranking our team 17th out of 29 participants by using another multilingual Transformer-based model, XLM-RoBERTa.</abstract>
<identifier type="citekey">zaharia-etal-2020-upb</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.179</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.179/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1322</start>
<end>1330</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UPB at SemEval-2020 Task 9: Identifying Sentiment in Code-Mixed Social Media Texts Using Transformers and Multi-Task Learning
%A Zaharia, George-Eduard
%A Vlad, George-Alexandru
%A Cercel, Dumitru-Clementin
%A Rebedea, Traian
%A Chiru, Costin
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y May, Jonathan
%Y Shutova, Ekaterina
%S Proceedings of the Fourteenth Workshop on Semantic Evaluation
%D 2020
%8 December
%I International Committee for Computational Linguistics
%C Barcelona (online)
%F zaharia-etal-2020-upb
%X Sentiment analysis is a process widely used in opinion mining campaigns conducted today. This phenomenon presents applications in a variety of fields, especially in collecting information related to the attitude or satisfaction of users concerning a particular subject. However, the task of managing such a process becomes noticeably more difficult when it is applied in cultures that tend to combine two languages in order to express ideas and thoughts. By interleaving words from two languages, the user can express with ease, but at the cost of making the text far less intelligible for those who are not familiar with this technique, but also for standard opinion mining algorithms. In this paper, we describe the systems developed by our team for SemEval-2020 Task 9 that aims to cover two well-known code-mixed languages: Hindi-English and Spanish-English. We intend to solve this issue by introducing a solution that takes advantage of several neural network approaches, as well as pre-trained word embeddings. Our approach (multlingual BERT) achieves promising performance on the Hindi-English task, with an average F1-score of 0.6850, registered on the competition leaderboard, ranking our team 16 out of 62 participants. For the Spanish-English task, we obtained an average F1-score of 0.7064 ranking our team 17th out of 29 participants by using another multilingual Transformer-based model, XLM-RoBERTa.
%R 10.18653/v1/2020.semeval-1.179
%U https://aclanthology.org/2020.semeval-1.179/
%U https://doi.org/10.18653/v1/2020.semeval-1.179
%P 1322-1330
Markdown (Informal)
[UPB at SemEval-2020 Task 9: Identifying Sentiment in Code-Mixed Social Media Texts Using Transformers and Multi-Task Learning](https://aclanthology.org/2020.semeval-1.179/) (Zaharia et al., SemEval 2020)
ACL