MasakhaNEWS: News Topic Classification for African languages
This addresses the lack of standardized datasets for African languages in NLP, providing a resource for researchers, but it is incremental as it builds on existing methods for low-resource settings.
The authors tackled the under-representation of African languages in NLP by creating MasakhaNEWS, a benchmark dataset for news topic classification across 16 languages, and evaluated baseline models, showing that prompting ChatGPT achieved 70 F1 points in zero-shot settings and pattern exploiting training reached 86.0 F1 points with 10 examples per label in few-shot settings.
African languages are severely under-represented in NLP research due to lack of datasets covering several NLP tasks. While there are individual language specific datasets that are being expanded to different tasks, only a handful of NLP tasks (e.g. named entity recognition and machine translation) have standardized benchmark datasets covering several geographical and typologically-diverse African languages. In this paper, we develop MasakhaNEWS -- a new benchmark dataset for news topic classification covering 16 languages widely spoken in Africa. We provide an evaluation of baseline models by training classical machine learning models and fine-tuning several language models. Furthermore, we explore several alternatives to full fine-tuning of language models that are better suited for zero-shot and few-shot learning such as cross-lingual parameter-efficient fine-tuning (like MAD-X), pattern exploiting training (PET), prompting language models (like ChatGPT), and prompt-free sentence transformer fine-tuning (SetFit and Cohere Embedding API). Our evaluation in zero-shot setting shows the potential of prompting ChatGPT for news topic classification in low-resource African languages, achieving an average performance of 70 F1 points without leveraging additional supervision like MAD-X. In few-shot setting, we show that with as little as 10 examples per label, we achieved more than 90\% (i.e. 86.0 F1 points) of the performance of full supervised training (92.6 F1 points) leveraging the PET approach.