Publication detail

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

APAROVICH, M. KESIRAJU, S. DUFKOVÁ, A. SMRŽ, P.

Original Title

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

Type

conference paper

Language

English

Original Abstract

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.

Keywords

sentiment analysis, cross-lingual sentiment analysis, domain adaptation, adversarial training, low-resource languages, African languages, transformer, feed-forward neural network

Authors

APAROVICH, M.; KESIRAJU, S.; DUFKOVÁ, A.; SMRŽ, P.

Released

21. 4. 2023

Publisher

Association for Computational Linguistics

Location

Toronto (online)

ISBN

978-1-959429-99-9

Book

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

Pages from

1518

Pages to

1524

Pages count

7

URL

https://aclanthology.org/2023.semeval-1.209/

BibTex

@inproceedings{BUT187994,
  author="Maksim {Aparovich} and Santosh {Kesiraju} and Aneta {Dufková} and Pavel {Smrž}",
  title="FIT BUT at SemEval-2023 Task 12: Sentiment Without Borders - Multilingual Domain Adaptation for Low-Resource Sentiment Classification",
  booktitle="Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023)",
  year="2023",
  pages="1518--1524",
  publisher="Association for Computational Linguistics",
  address="Toronto (online)",
  doi="10.18653/v1/2023.semeval-1.209",
  isbn="978-1-959429-99-9",
  url="https://aclanthology.org/2023.semeval-1.209/"
}