FIT BUT at SemEval-2023 Task 12: Sentiment Without Borders - Multilingual Domain Adaptation for Low-Resource Sentiment Classification

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F23%3APU150880" target="_blank" >RIV/00216305:26230/23:PU150880 - isvavai.cz</a>

Result on the web

<a href="https://aclanthology.org/2023.semeval-1.209/" target="_blank" >https://aclanthology.org/2023.semeval-1.209/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2023.semeval-1.209" target="_blank" >10.18653/v1/2023.semeval-1.209</a>

Result language

angličtina

Original language name

FIT BUT at SemEval-2023 Task 12: Sentiment Without Borders - Multilingual Domain Adaptation for Low-Resource Sentiment Classification

Original language description

This paper presents our proposed method for SemEval-2023 Task 12, which focuses on sentiment analysis for low-resource African lan- guages. 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.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/8A21015" target="_blank" >8A21015: AI-augmented automation for efficient DevOps, a model-based framework for continuous development At RunTime in cyber-physical systems</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2023

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023)

ISBN

978-1-959429-99-9

ISSN

—

e-ISSN

—

Number of pages

7

Pages from-to

1518-1524

Publisher name

Association for Computational Linguistics

Place of publication

Toronto (online)

Event location

Toronto

Event date

Jul 9, 2023

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—