AfriHG: News headline generation for African Languages
This addresses the problem of limited resources for African language NLP, though it is incremental as it builds on existing datasets and models.
The paper tackled news headline generation for 16 African languages by creating the AfriHG dataset and testing models, finding that Africa-centric models like AfriTeVa V2 outperformed multilingual mT5-base and were competitive with a much larger LLM.
This paper introduces AfriHG -- a news headline generation dataset created by combining from XLSum and MasakhaNEWS datasets focusing on 16 languages widely spoken by Africa. We experimented with two seq2eq models (mT5-base and AfriTeVa V2), and Aya-101 LLM. Our results show that Africa-centric seq2seq models such as AfriTeVa V2 outperform the massively multilingual mT5-base model. Finally, we show that the performance of fine-tuning AfriTeVa V2 with 313M parameters is competitive to prompting Aya-101 LLM with more than 13B parameters.