AfriHG: News headline generation for African Languages

Toyib Ogunremi, Serah Akojenu, Anthony Soronnadi, Olubayo Adekanmbi, David Ifeoluwa Adelani
12/28/2024
cs.CL

No official code found. Best implementation: dadelani/AfriHG (5 stars, Apache-2.0, last commit 2025-01-27).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

dadelani/AfriHGCommunity100%
Apache-2.0

News headline generation for African languages

50PythonDec 28, 20241 years agoApache-2.0

Cite this paper

@article{ogunremi2024afrihg,
  title  = {AfriHG: News headline generation for African Languages},
  author = {Toyib Ogunremi and Serah Akojenu and Anthony Soronnadi and Olubayo Adekanmbi and David Ifeoluwa Adelani},
  year   = {2024},
  eprint = {2412.20223},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2412.20223v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2412.20223.svg)](https://codeofpaper.com/paper/2412.20223)

Discussion