AfriKI: Machine-in-the-Loop Afrikaans Poetry Generation
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 16 of its 65 references that are in the map. First posted on arXiv 30 Mar 2021.
Builds on
16 of 65 references.
References · 16
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
- 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 789
- 2020Participatory Research for Low-resourced Machine Translation: A Case Study in African Languagescited by 159
- 2020Masakhane -- Machine Translation For Africacited by 48
- 2018Deep-speare: A Joint Neural Model of Poetic Language, Meter and Rhymecited by 35
- 2016Chinese Poetry Generation with Planning based Neural Networkcited by 22
- 2016Generating Chinese Classical Poems with RNN Encoder-Decodercited by 16
- 2020Cue Me In: Content-Inducing Approaches to Interactive Story Generationcited by 16
- 2017Generating Thematic Chinese Poetry using Conditional Variational Autoencoders with Hybrid Decoderscited by 12
4 more
- 2019COCO_TS Dataset: Pixel-level Annotations Based on Weak Supervision for Scene Text Segmentationcited by 12
- 2016Chinese Song Iambics Generation with Neural Attention-based Modelcited by 9
- 2019Deep Poetry: A Chinese Classical Poetry Generation Systemcited by 5
- 2019On How Users Edit Computer-Generated Visual Storiescited by 3
Built on by
Citing papers per year: 2024: 1.
1 paper.