Masakhane-Afrisenti at SemEval-2023 Task 12: Sentiment Analysis using Afro-centric Language Models and Adapters for Low-resource African Languages

Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 1311–1316 July 13-14, 2023 ©2023 Association for Computational Linguistics Masakhane-Afrisenti at SemEval-2023 Task 12: Sentiment Analysis using Afro-centric Language Models and Adapters for Low-resource African Languages Israel Abebe Azime1,†, Sana Sabah Al-Azzawi2,†, Atnafu Lambebo Tonja3,†, Iyanuoluwa Shode4, Jesujoba Alabi 1, Ayodele Awokoya 5, Mardiyyah Oduwole, Tosin Adewumi 2, Samuel Fanijo 7, Awosan Oyinkansola, Oreen Yousuf ∀Masakhane NLP, 1Saarland University, Germany, 2Luleå University of Technology, Sweden, 3Instituto Politécnico Nacional, Mexico, 4Montclair State University, USA, 5University of Ibadan, Nigeria, 6 Brandeis University, USA, 7Iowa State University, USA. Abstract In this paper, we describe our submission for the AfriSenti-SemEval Shared Task 12 of SemEval-2023 . The task aims to perform monolingual sentiment classification (sub-task A) for 12 African languages, multilingual senti- ment classification (sub-task B), and zero-shot sentiment classification (task C). For sub-task A, we conducted experiments using classical machine learning classifiers, Afro-centric lan- guage models, and language-specific models. For task B, we fine-tuned multilingual pre- trained language models that support many of the languages in the task. For task C, we made use of a parameter-efficient Adapter approach that leverages monolingual texts in the target language for effective zero-shot transfer. Our findings suggest that using pre-trained Afro- centric language models improves performance for low-resource African languages. We also ran experiments using adapters for zero-shot tasks, and the results suggest that we can ob- tain promising results by using adapters with limited resources. 1 Introduction Low-resourced languages receive less attention in natural language processing (NLP) research be- cause they lack the quality of datasets necessary for training, evaluation, and model implementation. However, the increasing abundance of social me- dia platforms on the internet is changing the game for these languages, giving them more visibility and accessibility. This was not always the case, as a significant amount of NLP research focused on sentiment analysis and other tasks geared toward specific languages having a high online presence, thus resulting in the creation of techniques and models tailored to their needs (Yimam et al., 2020; Muhammad et al., 2022). The rise of region-specific competitions such as the AfriSenti-SemEval competition has led to ef- †These authors contributed equally to this work. forts to curate quality datasets sourced from the internet, create new techniques to maximize the use of these datasets for NLP tasks and investigate the adequacy of existing NLP techniques to cater to the linguistic needs of low-resourced languages. The AfriSenti-SemEval Shared Task 12 provides a corpus of Twitter datasets written in 14 African languages for sentiment analysis tasks (Fröbe et al., 2023). This shared task presents a unique oppor- tunity to advance sentiment analysis development in local languages and help bridge the digital di- vide in this area. The hope is that this contribution will assist future research and developments in this field. This paper details our submission for the Afrisenti SemEval-2023 Task 12 (Muhammad et al., 2023b), which investigates the effective- ness of pre-trained Afro-centric language mod- els and adapters for sentiment …

Content truncated to 500 words