Automatic Arabic Poem Generation with GPT-2

Mohamed El Ghaly Beheitt, Moez Ben Haj Hmida

2022

Abstract

Automatically generating poetry by computers is a challenging topic that requires the use of advanced deep learning techniques. While much attention has been given to English and Chinese poem generation, there are few significant efforts considering other languages. Generating poems in Arabic is a difficult task due to the complexity of the Arabic language grammatical structure. In this paper, we investigate the feasibility of training generative pre-trained language model GPT-2 to generate Arabic poems. The results of the experiments, which included the BLEU score as well as human assessments, confirmed the effectiveness of our proposed model. Both automatic and human evaluations show that our proposed model outperforms existing models in generating Arabic poetry.

Paper Citation

in Harvard Style

Beheitt M. and Ben Haj Hmida M. (2022). Automatic Arabic Poem Generation with GPT-2. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-547-0, pages 366-374. DOI: 10.5220/0010847100003116

in Bibtex Style

@conference{icaart22,
author={Mohamed El Ghaly Beheitt and Moez Ben Haj Hmida},
title={Automatic Arabic Poem Generation with GPT-2},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2022},
pages={366-374},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010847100003116},
isbn={978-989-758-547-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Automatic Arabic Poem Generation with GPT-2
SN - 978-989-758-547-0
AU - Beheitt M.
AU - Ben Haj Hmida M.
PY - 2022
SP - 366
EP - 374
DO - 10.5220/0010847100003116