Dr. Idris Abdulmumin

Room 5-49 IT Building,

University of Pretoria,

Hatfield Campus

I am a Postdoctoral Fellow at the University of Pretoria’s Data Science for Social Impact Research Group, working on improving Natural Language Processing (NLP) for underrepresented African languages. I hold a PhD from Bayero University Kano, where I focused on using domain awareness, quality estimation, and transfer learning to optimize approaches for leveraging monolingual data to enhance machine translation in low-resource languages.

I have led and contributed to a range of impactful projects, including developing NLP resources and techniques for tasks such as LLM building, sentiment analysis, emotion analysis, semantic relatedness, hate and offensive speech analysis, machine translation, named-entity recognition, and sentence alignment. I actively collaborate with international research communities such as Masakhane, HausaNLP, LITHME, and the Open Language Data Initiative, and have contributed to several Semantic Evaluation shared tasks: AfriSenti 2023, SemRel 2024, and BRIGHTER 2025.

I’m passionate about mentoring students and early-career researchers, and I strive to integrate ethical, human-centric approaches into my work, aligning with my commitment to advancing NLP for social good. My research is driven by the belief that AI should be inclusive and accessible, and I aim to make meaningful contributions to the field while addressing the needs of underrepresented communities.

latest posts

May 04, 2025	🛰️ May the 4th Be With You! “In a research lab not so far away…” While… \| Data Science for Social Impact

selected publications

DiB

ZASCA-Sum: A Dataset of the South Africa Supreme Courts of Appeal Judgments and Media Summaries for Legal Documents Summarization Research

Idris Abdulmumin and Vukosi Marivate

Data in Brief, 2025

DOI Bib

@article{ABDULMUMIN2025111567,
  title = {ZASCA-Sum: A Dataset of the South Africa Supreme Courts of Appeal Judgments and Media Summaries for Legal Documents Summarization Research},
  journal = {Data in Brief},
  pages = {111567},
  year = {2025},
  issn = {2352-3409},
  doi = {https://doi.org/10.1016/j.dib.2025.111567},
  url = {https://www.sciencedirect.com/science/article/pii/S2352340925002999},
  author = {Abdulmumin, Idris and Marivate, Vukosi}
}

Mach. Trans.

Tag-less back-translation

Idris Abdulmumin, Bashir Shehu Galadanci, and Garba Aliyu

Machine Translation, Dec 2021

DOI Bib

@article{Abdulmumin2021-tagless-mach-trans,
  doi = {10.1007/s10590-021-09284-y},
  year = {2021},
  month = dec,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {35},
  number = {4},
  pages = {519--549},
  author = {Abdulmumin, Idris and Galadanci, Bashir Shehu and Aliyu, Garba},
  title = {Tag-less back-translation},
  journal = {Machine Translation},
  url = {https://link.springer.com/article/10.1007/s10590-021-09284-y}
}

LREC

Hausa Visual Genome: A Dataset for Multi-Modal English to Hausa Machine Translation

Idris Abdulmumin, Satya Ranjan Dash, Musa Abdullahi Dawud, and 7 more authors

In Proceedings of the Language Resources and Evaluation Conference, Jun 2022

Bib

@inproceedings{abdulmumin-EtAl:2022:LREC,
  author = {Abdulmumin, Idris and Dash, Satya Ranjan and Dawud, Musa Abdullahi and Parida, Shantipriya and Muhammad, Shamsuddeen and Ahmad, Ibrahim Said and Panda, Subhadarshi and Bojar, Ond{\v{r}}ej and Galadanci, Bashir Shehu and Bello, Bello Shehu},
  title = {Hausa Visual Genome: A Dataset for Multi-Modal English to Hausa Machine Translation},
  booktitle = {Proceedings of the Language Resources and Evaluation Conference},
  month = jun,
  year = {2022},
  address = {Marseille, France},
  publisher = {European Language Resources Association},
  pages = {6471--6479},
  url = {https://aclanthology.org/2022.lrec-1.694}
}

ICCAIT

Leveraging Closed-Access Multilingual Embedding for Automatic Sentence Alignment in Low Resource Languages

Idris Abdulmumin, Auwal Abubakar Khalid, Shamsuddeen Hassan Muhammad, and 5 more authors

In Proceedings of the International Conference on Computing and Advances in Information Technology (ICCAIT 2023), Nov 2023

Bib

@inproceedings{abdulmumin2023leveraging,
  title = {Leveraging Closed-Access Multilingual Embedding for Automatic Sentence Alignment in Low Resource Languages},
  author = {Abdulmumin, Idris and Khalid, Auwal Abubakar and Muhammad, Shamsuddeen Hassan and Ahmad, Ibrahim Said and Aliyu, Lukman Jibril and Sani, Babangida and Abduljalil, Bala Mairiga and Hassan, Sani Ahmad},
  year = {2023},
  month = nov,
  booktitle = {Proceedings of the International Conference on Computing and Advances in Information Technology ({ICCAIT} 2023)},
  address = {Zaria, Nigeria},
  url = {https://arxiv.org/abs/2311.12179}
}

EMNLP

AfriSenti: A Twitter Sentiment Analysis Benchmark for African Languages

Shamsuddeen Muhammad, Idris Abdulmumin, Abinew Ayele, and 24 more authors

In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Dec 2023

Bib

@inproceedings{muhammad-etal-2023-afrisenti,
  title = {{A}fri{S}enti: A {T}witter Sentiment Analysis Benchmark for {A}frican Languages},
  author = {Muhammad, Shamsuddeen and Abdulmumin, Idris and Ayele, Abinew and Ousidhoum, Nedjma and Adelani, David and Yimam, Seid and Ahmad, Ibrahim and Beloucif, Meriem and Mohammad, Saif and Ruder, Sebastian and Hourrane, Oumaima and Jorge, Alipio and Brazdil, Pavel and Ali, Felermino and David, Davis and Osei, Salomey and Shehu-Bello, Bello and Lawan, Falalu and Gwadabe, Tajuddeen and Rutunda, Samuel and Belay, Tadesse and Messelle, Wendimu and Balcha, Hailu and Chala, Sisay and Gebremichael, Hagos and Opoku, Bernard and Arthur, Stephen},
  editor = {Bouamor, Houda and Pino, Juan and Bali, Kalika},
  booktitle = {Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing},
  month = dec,
  year = {2023},
  address = {Singapore},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2023.emnlp-main.862},
  pages = {13968--13981}
}