AfriHG: News headline generation for African Languages
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916545149534208 |
|---|---|
| author | Ogunremi, Toyib Akojenu, Serah Soronnadi, Anthony Adekanmbi, Olubayo Adelani, David Ifeoluwa |
| author_facet | Ogunremi, Toyib Akojenu, Serah Soronnadi, Anthony Adekanmbi, Olubayo Adelani, David Ifeoluwa |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_20223 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AfriHG: News headline generation for African Languages Ogunremi, Toyib Akojenu, Serah Soronnadi, Anthony Adekanmbi, Olubayo Adelani, David Ifeoluwa Computation and Language 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. |
| title | AfriHG: News headline generation for African Languages |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2412.20223 |