@inproceedings{aparovich-etal-2023-fit,
title = "{FIT} {BUT} at {S}em{E}val-2023 Task 12: Sentiment Without Borders - Multilingual Domain Adaptation for Low-Resource Sentiment Classification",
author = "Aparovich, Maksim and
Kesiraju, Santosh and
Dufkova, Aneta and
Smrz, Pavel",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Da San Martino, Giovanni and
Tayyar Madabushi, Harish and
Kumar, Ritesh and
Sartori, Elisa},
booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.semeval-1.209",
doi = "10.18653/v1/2023.semeval-1.209",
pages = "1518--1524",
abstract = "This paper presents our proposed method for SemEval-2023 Task 12, which focuses on sentiment analysis for low-resource African languages. Our method utilizes a language-centric domain adaptation approach which is based on adversarial training, where a small version of Afro-XLM-Roberta serves as a generator model and a feed-forward network as a discriminator. We participated in all three subtasks: monolingual (12 tracks), multilingual (1 track), and zero-shot (2 tracks). Our results show an improvement in weighted F1 for 13 out of 15 tracks with a maximum increase of 4.3 points for Moroccan Arabic compared to the baseline. We observed that using language family-based labels along with sequence-level input representations for the discriminator model improves the quality of the cross-lingual sentiment analysis for the languages unseen during the training. Additionally, our experimental results suggest that training the system on languages that are close in a language families tree enhances the quality of sentiment analysis for low-resource languages. Lastly, the computational complexity of the prediction step was kept at the same level which makes the approach to be interesting from a practical perspective. The code of the approach can be found in our repository.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aparovich-etal-2023-fit">
<titleInfo>
<title>FIT BUT at SemEval-2023 Task 12: Sentiment Without Borders - Multilingual Domain Adaptation for Low-Resource Sentiment Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maksim</namePart>
<namePart type="family">Aparovich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">Kesiraju</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aneta</namePart>
<namePart type="family">Dufkova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Smrz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Sartori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents our proposed method for SemEval-2023 Task 12, which focuses on sentiment analysis for low-resource African languages. Our method utilizes a language-centric domain adaptation approach which is based on adversarial training, where a small version of Afro-XLM-Roberta serves as a generator model and a feed-forward network as a discriminator. We participated in all three subtasks: monolingual (12 tracks), multilingual (1 track), and zero-shot (2 tracks). Our results show an improvement in weighted F1 for 13 out of 15 tracks with a maximum increase of 4.3 points for Moroccan Arabic compared to the baseline. We observed that using language family-based labels along with sequence-level input representations for the discriminator model improves the quality of the cross-lingual sentiment analysis for the languages unseen during the training. Additionally, our experimental results suggest that training the system on languages that are close in a language families tree enhances the quality of sentiment analysis for low-resource languages. Lastly, the computational complexity of the prediction step was kept at the same level which makes the approach to be interesting from a practical perspective. The code of the approach can be found in our repository.</abstract>
<identifier type="citekey">aparovich-etal-2023-fit</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.209</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.209</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1518</start>
<end>1524</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FIT BUT at SemEval-2023 Task 12: Sentiment Without Borders - Multilingual Domain Adaptation for Low-Resource Sentiment Classification
%A Aparovich, Maksim
%A Kesiraju, Santosh
%A Dufkova, Aneta
%A Smrz, Pavel
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Da San Martino, Giovanni
%Y Tayyar Madabushi, Harish
%Y Kumar, Ritesh
%Y Sartori, Elisa
%S Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F aparovich-etal-2023-fit
%X This paper presents our proposed method for SemEval-2023 Task 12, which focuses on sentiment analysis for low-resource African languages. Our method utilizes a language-centric domain adaptation approach which is based on adversarial training, where a small version of Afro-XLM-Roberta serves as a generator model and a feed-forward network as a discriminator. We participated in all three subtasks: monolingual (12 tracks), multilingual (1 track), and zero-shot (2 tracks). Our results show an improvement in weighted F1 for 13 out of 15 tracks with a maximum increase of 4.3 points for Moroccan Arabic compared to the baseline. We observed that using language family-based labels along with sequence-level input representations for the discriminator model improves the quality of the cross-lingual sentiment analysis for the languages unseen during the training. Additionally, our experimental results suggest that training the system on languages that are close in a language families tree enhances the quality of sentiment analysis for low-resource languages. Lastly, the computational complexity of the prediction step was kept at the same level which makes the approach to be interesting from a practical perspective. The code of the approach can be found in our repository.
%R 10.18653/v1/2023.semeval-1.209
%U https://aclanthology.org/2023.semeval-1.209
%U https://doi.org/10.18653/v1/2023.semeval-1.209
%P 1518-1524
Markdown (Informal)
[FIT BUT at SemEval-2023 Task 12: Sentiment Without Borders - Multilingual Domain Adaptation for Low-Resource Sentiment Classification](https://aclanthology.org/2023.semeval-1.209) (Aparovich et al., SemEval 2023)
ACL