AfriKI: Machine-in-the-Loop Afrikaans Poetry Generation
Computation and Language
2021-03-31 v1 Machine Learning
Abstract
This paper proposes a generative language model called AfriKI. Our approach is based on an LSTM architecture trained on a small corpus of contemporary fiction. With the aim of promoting human creativity, we use the model as an authoring tool to explore machine-in-the-loop Afrikaans poetry generation. To our knowledge, this is the first study to attempt creative text generation in Afrikaans.
Cite
@article{arxiv.2103.16190,
title = {AfriKI: Machine-in-the-Loop Afrikaans Poetry Generation},
author = {Imke van Heerden and Anil Bas},
journal= {arXiv preprint arXiv:2103.16190},
year = {2021}
}
Comments
Accepted to EACL 2021 Workshop on AfricaNLP (non-archival)