Publications | Dr. Idris Abdulmumin

2025

NAACL

AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages

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

In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), Apr 2025

Bib

@inproceedings{muhammad-etal-2025-afrihate,
  title = {{A}fri{H}ate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for {A}frican Languages},
  author = {Muhammad, Shamsuddeen Hassan and Abdulmumin, Idris and Ayele, Abinew Ali and Adelani, David Ifeoluwa and Ahmad, Ibrahim Said and Aliyu, Saminu Mohammad and R{\"o}ttger, Paul and Oppong, Abigail and Bukula, Andiswa and Chukwuneke, Chiamaka Ijeoma and Jibril, Ebrahim Chekol and Ismail, Elyas Abdi and Alemneh, Esubalew and Gebremichael, Hagos Tesfahun and Aliyu, Lukman Jibril and Beloucif, Meriem and Hourrane, Oumaima and Mabuya, Rooweither and Osei, Salomey and Rutunda, Samuel and Belay, Tadesse Destaw and Guge, Tadesse Kebede and Asfaw, Tesfa Tegegne and Wanzare, Lilian Diana Awuor and Onyango, Nelson Odhiambo and Yimam, Seid Muhie and Ousidhoum, Nedjma},
  editor = {Chiruzzo, Luis and Ritter, Alan and Wang, Lu},
  booktitle = {Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)},
  month = apr,
  year = {2025},
  address = {Albuquerque, New Mexico},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2025.naacl-long.92/},
  pages = {1854--1871},
  isbn = {979-8-89176-189-6}
}

arXiv

BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages

Shamsuddeen Hassan Muhammad, Nedjma Ousidhoum, Idris Abdulmumin, and 45 more authors

Apr 2025

Bib

@misc{muhammad2025brighterbridginggaphumanannotated,
  title = {BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages},
  author = {Muhammad, Shamsuddeen Hassan and Ousidhoum, Nedjma and Abdulmumin, Idris and Wahle, Jan Philip and Ruas, Terry and Beloucif, Meriem and de Kock, Christine and Surange, Nirmal and Teodorescu, Daniela and Ahmad, Ibrahim Said and Adelani, David Ifeoluwa and Aji, Alham Fikri and Ali, Felermino D. M. A. and Alimova, Ilseyar and Araujo, Vladimir and Babakov, Nikolay and Baes, Naomi and Bucur, Ana-Maria and Bukula, Andiswa and Cao, Guanqun and Cardenas, Rodrigo Tufino and Chevi, Rendi and Chukwuneke, Chiamaka Ijeoma and Ciobotaru, Alexandra and Dementieva, Daryna and Gadanya, Murja Sani and Geislinger, Robert and Gipp, Bela and Hourrane, Oumaima and Ignat, Oana and Lawan, Falalu Ibrahim and Mabuya, Rooweither and Mahendra, Rahmad and Marivate, Vukosi and Piper, Andrew and Panchenko, Alexander and Ferreira, Charles Henrique Porto and Protasov, Vitaly and Rutunda, Samuel and Shrivastava, Manish and Udrea, Aura Cristina and Wanzare, Lilian Diana Awuor and Wu, Sophie and Wunderlich, Florian Valentin and Zhafran, Hanif Muhammad and Zhang, Tianhui and Zhou, Yi and Mohammad, Saif M.},
  year = {2025},
  eprint = {2502.11926},
  archiveprefix = {arXiv},
  primaryclass = {cs.CL},
  url = {https://arxiv.org/abs/2502.11926}
}

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, Apr 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}
}

2024

SemEval

SemEval Task 1: Semantic Textual Relatedness for African and Asian Languages

Nedjma Ousidhoum, Shamsuddeen Hassan Muhammad, Mohamed Abdalla, and 14 more authors

In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), Jun 2024

DOI Bib

@inproceedings{ousidhoum-etal-2024-semeval,
  title = {{S}em{E}val Task 1: Semantic Textual Relatedness for {A}frican and {A}sian Languages},
  author = {Ousidhoum, Nedjma and Muhammad, Shamsuddeen Hassan and Abdalla, Mohamed and Abdulmumin, Idris and Ahmad, Ibrahim Said and Ahuja, Sanchit and Aji, Alham Fikri and Araujo, Vladimir and Beloucif, Meriem and De Kock, Christine and Hourrane, Oumaima and Shrivastava, Manish and Solorio, Thamar and Surange, Nirmal and Vishnubhotla, Krishnapriya and Yimam, Seid Muhie and Mohammad, Saif M.},
  editor = {Ojha, Atul Kr. and Do{\u{g}}ru{\"o}z, A. Seza and Tayyar Madabushi, Harish and Da San Martino, Giovanni and Rosenthal, Sara and Ros{\'a}, Aiala},
  booktitle = {Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)},
  month = jun,
  year = {2024},
  address = {Mexico City, Mexico},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2024.semeval-1.272},
  doi = {10.18653/v1/2024.semeval-1.272},
  pages = {1963--1978}
}

LREC-COLING

Mitigating Translationese in Low-resource Languages: The Storyboard Approach

Garry Kuwanto, Eno-Abasi E. Urua, Priscilla Amondi Amuok, and 21 more authors

In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), May 2024

Bib

@inproceedings{kuwanto-etal-2024-mitigating-translationese,
  title = {Mitigating Translationese in Low-resource Languages: The Storyboard Approach},
  author = {Kuwanto, Garry and Urua, Eno-Abasi E. and Amuok, Priscilla Amondi and Muhammad, Shamsuddeen Hassan and Aremu, Anuoluwapo and Otiende, Verrah and Nanyanga, Loice Emma and Nyoike, Teresiah W. and Akpan, Aniefon D. and Udouboh, Nsima Ab and Archibong, Idongesit Udeme and Moses, Idara Effiong and Ige, Ifeoluwatayo A. and Ajibade, Benjamin and Awokoya, Olumide Benjamin and Abdulmumin, Idris and Aliyu, Saminu Mohammad and Iro, Ruqayya Nasir and Ahmad, Ibrahim Said and Smith, Deontae and Michaels, Praise-EL and Adelani, David Ifeoluwa and Wijaya, Derry Tanti and Andy, Anietie},
  editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen},
  booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
  month = may,
  year = {2024},
  address = {Torino, Italy},
  publisher = {ELRA and ICCL},
  url = {https://aclanthology.org/2024.lrec-main.992},
  pages = {11349--11360}
}

SIGIR

CIRAL: A Test Collection for CLIR Evaluation in African Languages

Mofetoluwa Adeyemi, Akintunde Oladipo, Xinyu Zhang, and 20 more authors

In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul 2024

DOI Bib

@inproceedings{10.1145/3626772.3657884,
  author = {Adeyemi, Mofetoluwa and Oladipo, Akintunde and Zhang, Xinyu and Alfonso-Hermelo, David and Rezagholizadeh, Mehdi and Chen, Boxing and Omotayo, Abdul-Hakeem and Abdulmumin, Idris and Etori, Naome A. and Musa, Toyib Babatunde and Fanijo, Samuel and Awoyomi, Oluwabusayo Olufunke and Salahudeen, Saheed Abdullahi and Mohammed, Labaran Adamu and Abolade, Daud Olamide and Lawan, Falalu Ibrahim and Abubakar, Maryam Sabo and Iro, Ruqayya Nasir and Abubakar, Amina Imam and Mohamed, Shafie Abdi and Mohamed, Hanad Mohamud and Ajayi, Tunde Oluwaseyi and Lin, Jimmy},
  booktitle = {Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  title = {CIRAL: A Test Collection for CLIR Evaluation in African Languages},
  month = jul,
  year = {2024},
  address = {Washington, DC, USA},
  publisher = {Association for Computing Machinery},
  doi = {10.1145/3626772.3657884},
  url = {https://doi.org/10.1145/3626772.3657884},
  series = {SIGIR '24}
}

SACAIR

Analysing Public Transport User Sentiment on Low Resource Multilingual Data

Rozina Myoya, Vukosi Marivate, and Idris Abdulmumin

In Proceedings of the Fifth Southern African Conference for Artificial Intelligence Research, Jul 2024

Bib

@inproceedings{myoya2024-sacair,
  author = {Myoya, Rozina and Marivate, Vukosi and Abdulmumin, Idris},
  title = {Analysing Public Transport User Sentiment on Low Resource Multilingual Data},
  booktitle = {Proceedings of the Fifth Southern African Conference for Artificial Intelligence Research},
  year = {2024},
  address = {Bloemfontein, South Africa},
  editor = {Gerber, Aurona and Maritz, Jacques and Pillay, Anban},
  url = {https://2024.sacair.org.za/proceedings}
}

WOAH

HausaHate: An Expert Annotated Corpus for Hausa Hate Speech Detection

Francielle Vargas, Samuel Guimarães, Shamsuddeen Hassan Muhammad, and 6 more authors

In Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024), Jun 2024

DOI Bib

@inproceedings{vargas-etal-2024-hausahate,
  title = {{H}ausa{H}ate: An Expert Annotated Corpus for {H}ausa Hate Speech Detection},
  author = {Vargas, Francielle and Guimar{\~a}es, Samuel and Muhammad, Shamsuddeen Hassan and Alves, Diego and Ahmad, Ibrahim Said and Abdulmumin, Idris and Mohamed, Diallo and Pardo, Thiago and Benevenuto, Fabr{\'\i}cio},
  editor = {Chung, Yi-Ling and Talat, Zeerak and Nozza, Debora and Plaza-del-Arco, Flor Miriam and R{\"o}ttger, Paul and Mostafazadeh Davani, Aida and Calabrese, Agostina},
  booktitle = {Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024)},
  month = jun,
  year = {2024},
  address = {Mexico City, Mexico},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2024.woah-1.5},
  doi = {10.18653/v1/2024.woah-1.5},
  pages = {52--58}
}

WMT

Correcting FLORES Evaluation Dataset for Four African Languages

Idris Abdulmumin, Sthembiso Mkhwanazi, Mahlatse Mbooi, and 7 more authors

In Proceedings of the Ninth Conference on Machine Translation, Nov 2024

DOI Bib

@inproceedings{abdulmumin-etal-2024-correcting,
  title = {Correcting {FLORES} Evaluation Dataset for Four {A}frican Languages},
  author = {Abdulmumin, Idris and Mkhwanazi, Sthembiso and Mbooi, Mahlatse and Muhammad, Shamsuddeen Hassan and Ahmad, Ibrahim Said and Putini, Neo and Mathebula, Miehleketo and Shingange, Matimba and Gwadabe, Tajuddeen and Marivate, Vukosi},
  editor = {Haddow, Barry and Kocmi, Tom and Koehn, Philipp and Monz, Christof},
  booktitle = {Proceedings of the Ninth Conference on Machine Translation},
  month = nov,
  year = {2024},
  address = {Miami, Florida, USA},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2024.wmt-1.44},
  doi = {10.18653/v1/2024.wmt-1.44},
  pages = {570--578}
}

WMT

Findings of WMT2024 English-to-Low Resource Multimodal Translation Task

Shantipriya Parida, Ondřej Bojar, Idris Abdulmumin, and 2 more authors

In Proceedings of the Ninth Conference on Machine Translation, Nov 2024

DOI Bib

@inproceedings{parida-etal-2024-findings,
  title = {Findings of {WMT}2024 {E}nglish-to-Low Resource Multimodal Translation Task},
  author = {Parida, Shantipriya and Bojar, Ond{\v{r}}ej and Abdulmumin, Idris and Muhammad, Shamsuddeen Hassan and Ahmad, Ibrahim Said},
  editor = {Haddow, Barry and Kocmi, Tom and Koehn, Philipp and Monz, Christof},
  booktitle = {Proceedings of the Ninth Conference on Machine Translation},
  month = nov,
  year = {2024},
  address = {Miami, Florida, USA},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2024.wmt-1.56},
  doi = {10.18653/v1/2024.wmt-1.56},
  pages = {677--683}
}

ACL

SemRel2024: A Collection of Semantic Textual Relatedness Datasets for 13 Languages

Nedjma Ousidhoum, Shamsuddeen Muhammad, Mohamed Abdalla, and 24 more authors

In Findings of the Association for Computational Linguistics: ACL 2024, Aug 2024

DOI Bib

@inproceedings{ousidhoum-etal-2024-semrel2024,
  title = {{S}em{R}el2024: A Collection of Semantic Textual Relatedness Datasets for 13 Languages},
  author = {Ousidhoum, Nedjma and Muhammad, Shamsuddeen and Abdalla, Mohamed and Abdulmumin, Idris and Ahmad, Ibrahim and Ahuja, Sanchit and Aji, Alham and Araujo, Vladimir and Ayele, Abinew and Baswani, Pavan and Beloucif, Meriem and Biemann, Chris and Bourhim, Sofia and Kock, Christine and Dekebo, Genet and Hourrane, Oumaima and Kanumolu, Gopichand and Madasu, Lokesh and Rutunda, Samuel and Shrivastava, Manish and Solorio, Thamar and Surange, Nirmal and Tilaye, Hailegnaw and Vishnubhotla, Krishnapriya and Winata, Genta and Yimam, Seid and Mohammad, Saif},
  editor = {Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2024},
  month = aug,
  year = {2024},
  address = {Bangkok, Thailand},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2024.findings-acl.147},
  doi = {10.18653/v1/2024.findings-acl.147},
  pages = {2512--2530}
}

2023

ACL

HaVQA: A Dataset for Visual Question Answering and Multimodal Research in Hausa Language

Shantipriya Parida, Idris Abdulmumin, Shamsuddeen Hassan Muhammad, and 7 more authors

In Findings of the Association for Computational Linguistics: ACL 2023, Jul 2023

Bib

@inproceedings{parida-etal-2023-havqa,
  title = {{H}a{VQA}: A Dataset for Visual Question Answering and Multimodal Research in {H}ausa Language},
  author = {Parida, Shantipriya and Abdulmumin, Idris and Muhammad, Shamsuddeen Hassan and Bose, Aneesh and Kohli, Guneet Singh and Ahmad, Ibrahim Said and Kotwal, Ketan and Deb Sarkar, Sayan and Bojar, Ond{\v{r}}ej and Kakudi, Habeebah},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2023},
  month = jul,
  year = {2023},
  address = {Toronto, Canada},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2023.findings-acl.646},
  pages = {10162--10183}
}

SemEval

HausaNLP at SemEval-2023 Task 10: Transfer Learning, Synthetic Data and Side-information for Multi-level Sexism Classification

Saminu Mohammad Aliyu, Idris Abdulmumin, Shamsuddeen Hassan Muhammad, and 4 more authors

In Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023), Jul 2023

Bib

@inproceedings{aliyu-etal-2023-hausanlp,
  title = {{H}ausa{NLP} at {S}em{E}val-2023 Task 10: Transfer Learning, Synthetic Data and Side-information for Multi-level Sexism Classification},
  author = {Aliyu, Saminu Mohammad and Abdulmumin, Idris and Muhammad, Shamsuddeen Hassan and Ahmad, Ibrahim Said and Salahudeen, Saheed Abdullahi and Yusuf, Aliyu and Lawan, Falalu Ibrahim},
  booktitle = {Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023)},
  month = jul,
  year = {2023},
  address = {Toronto, Canada},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2023.semeval-1.273},
  pages = {1983--1987}
}

ICCAIT

Analyzing COVID-19 Vaccination Sentiments in Nigerian Cyberspace: Insights from a Manually Annotated Twitter Dataset

Ibrahim Said Ahmad, Lukman Jibril Aliyu, Auwal Abubakar Khalid, and 6 more authors

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

Bib

@inproceedings{abdulmumin2023covid,
  title = {Analyzing COVID-19 Vaccination Sentiments in Nigerian Cyberspace: Insights from a Manually Annotated Twitter Dataset},
  author = {Ahmad, Ibrahim Said and Aliyu, Lukman Jibril and Khalid, Auwal Abubakar and Aliyu, Saminu Muhammad and Muhammad, Shamsuddeen Hassan and Abdulmumin, Idris and Abduljalil, Bala Mairiga and Shehu, Bello Shehu and Abubakar, Amina Imam},
  year = {2023},
  month = nov,
  booktitle = {Proceedings of the International Conference on Computing and Advances in Information Technology ({ICCAIT} 2023)},
  address = {Zaria, Nigeria}
}

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}
}

SemEval

SemEval-2023 Task 12: Sentiment Analysis for African Languages (AfriSenti-SemEval)

Shamsuddeen Hassan Muhammad, Idris Abdulmumin, Seid Muhie Yimam, and 7 more authors

In Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023), Jul 2023

Bib

@inproceedings{muhammad-etal-2023-semeval,
  title = {{S}em{E}val-2023 Task 12: Sentiment Analysis for {A}frican Languages ({A}fri{S}enti-{S}em{E}val)},
  author = {Muhammad, Shamsuddeen Hassan and Abdulmumin, Idris and Yimam, Seid Muhie and Adelani, David Ifeoluwa and Ahmad, Ibrahim Said and Ousidhoum, Nedjma and Ayele, Abinew Ali and Mohammad, Saif and Beloucif, Meriem and Ruder, Sebastian},
  booktitle = {Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023)},
  month = jul,
  year = {2023},
  address = {Toronto, Canada},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2023.semeval-1.315},
  pages = {2319--2337}
}

IJCNLP

MasakhaNEWS: News Topic Classification for African languages

David Ifeoluwa Adelani, Marek Masiak, Israel Abebe Azime, and 62 more authors

In Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, Nov 2023

Bib

@inproceedings{adelani-EtAl:2023:ijcnlp,
  author = {Adelani, David Ifeoluwa and Masiak, Marek and Azime, Israel Abebe and Alabi, Jesujoba and Tonja, Atnafu Lambebo and Mwase, Christine and Ogundepo, Odunayo and Dossou, Bonaventure F. P. and Oladipo, Akintunde and Nixdorf, Doreen and Emezue, Chris Chinenye and al-azzawi, sana and Sibanda, Blessing and David, Davis and Ndolela, Lolwethu and Mukiibi, Jonathan and Ajayi, Tunde and Moteu, Tatiana and Odhiambo, Brian and Owodunni, Abraham and Obiefuna, Nnaemeka and Mohamed, Muhidin and Muhammad, Shamsuddeen Hassan and Ababu, Teshome Mulugeta and Salahudeen, Saheed Abdullahi and Yigezu, Mesay Gemeda and Gwadabe, Tajuddeen and Abdulmumin, Idris and Taye, Mahlet and Awoyomi, Oluwabusayo and Shode, Iyanuoluwa and Adelani, Tolulope and Abdulganiyu, Habiba and Omotayo, Abdul-Hakeem and Adeeko, Adetola and Afolabi, Abeeb and Aremu, Anuoluwapo and Samuel, Olanrewaju and Siro, Clemencia and Kimotho, Wangari and Ogbu, Onyekachi and Mbonu, Chinedu and Chukwuneke, Chiamaka and Fanijo, Samuel and Ojo, Jessica and Awosan, Oyinkansola and Kebede, Tadesse and Sakayo, Toadoum Sari and Nyatsine, Pamela and Sidume, Freedmore and Yousuf, Oreen and Oduwole, Mardiyyah and Tshinu, kanda and Kimanuka, Ussen and Diko, Thina and Nxakama, Siyanda and Nigusse, Sinodos and Johar, Abdulmejid and Mohamed, Shafie and Hassan, Fuad Mire and Mehamed, Moges Ahmed and Ngabire, Evrard and Jules, Jules and Ssenkungu, Ivan and Stenetorp, Pontus},
  title = {MasakhaNEWS: News Topic Classification for African languages},
  booktitle = {Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics},
  month = nov,
  year = {2023},
  address = {Nusa Dua, Bali},
  publisher = {Association for Computational Linguistics},
  pages = {144--159},
  url = {https://aclanthology.org/2023.ijcnlp-long.10}
}

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}
}

2022

LREC

NaijaSenti: A Nigerian Twitter Sentiment Corpus for Multilingual Sentiment Analysis

Shamsuddeen Hassan Muhammad, David Ifeoluwa Adelani, Sebastian Ruder, and 8 more authors

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

Bib

@inproceedings{muhammad-EtAl:2022:LREC,
  author = {Muhammad, Shamsuddeen Hassan and Adelani, David Ifeoluwa and Ruder, Sebastian and Ahmad, Ibrahim Sa’id and Abdulmumin, Idris and Bello, Bello Shehu and Choudhury, Monojit and Emezue, Chris Chinenye and Abdullahi, Saheed Salahudeen and Aremu, Anuoluwapo and Brazdil, Pavel},
  title = {NaijaSenti: A Nigerian Twitter Sentiment Corpus for Multilingual Sentiment Analysis},
  booktitle = {Proceedings of the Language Resources and Evaluation Conference},
  month = jun,
  year = {2022},
  address = {Marseille, France},
  publisher = {European Language Resources Association},
  pages = {590--602},
  url = {https://aclanthology.org/2022.lrec-1.63}
}

NAACL

A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation

David Adelani, Jesujoba Alabi, Angela Fan, and 42 more authors

In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Jul 2022

Bib

@inproceedings{adelani-etal-2022-thousand,
  title = {A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for {A}frican News Translation},
  author = {Adelani, David and Alabi, Jesujoba and Fan, Angela and Kreutzer, Julia and Shen, Xiaoyu and Reid, Machel and Ruiter, Dana and Klakow, Dietrich and Nabende, Peter and Chang, Ernie and Gwadabe, Tajuddeen and Sackey, Freshia and Dossou, Bonaventure F. P. and Emezue, Chris and Leong, Colin and Beukman, Michael and Muhammad, Shamsuddeen and Jarso, Guyo and Yousuf, Oreen and Niyongabo Rubungo, Andre and Hacheme, Gilles and Wairagala, Eric Peter and Nasir, Muhammad Umair and Ajibade, Benjamin and Ajayi, Tunde and Gitau, Yvonne and Abbott, Jade and Ahmed, Mohamed and Ochieng, Millicent and Aremu, Anuoluwapo and Ogayo, Perez and Mukiibi, Jonathan and Ouoba Kabore, Fatoumata and Kalipe, Godson and Mbaye, Derguene and Tapo, Allahsera Auguste and Memdjokam Koagne, Victoire and Munkoh-Buabeng, Edwin and Wagner, Valencia and Abdulmumin, Idris and Awokoya, Ayodele and Buzaaba, Happy and Sibanda, Blessing and Bukula, Andiswa and Manthalu, Sam},
  booktitle = {Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  month = jul,
  year = {2022},
  address = {Seattle, United States},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2022.naacl-main.223},
  pages = {3053--3070}
}

AfricaNLP

NECAT-CLWE: A Simple But Efficient Parallel Data Generation Approach for Unsupervised and Semi-Supervised Neural Machine Translation

Rabiu Abdullahi Ibrahim and Idris Abdulmumin

In 3rd Workshop on African Natural Language Processing, Jul 2022

Bib

@inproceedings{ibrahim2022necatclwe,
  title = {{NECAT}-{CLWE}: A Simple But Efficient Parallel Data Generation Approach for Unsupervised and Semi-Supervised Neural Machine Translation},
  author = {Ibrahim, Rabiu Abdullahi and Abdulmumin, Idris},
  booktitle = {3rd Workshop on African Natural Language Processing},
  year = {2022},
  url = {https://openreview.net/forum?id=ruW4c9fNLZ5}
}

AfricaNLP

The African Stopwords Project: Curating Stopwords for African Languages

Chris Chinenye Emezue, Hellina Hailu Nigatu, Cynthia Thinwa, and 12 more authors

In 3rd Workshop on African Natural Language Processing, Jul 2022

Bib

@inproceedings{emezue2021the,
  title = {The African Stopwords Project: Curating Stopwords for African Languages},
  author = {Emezue, Chris Chinenye and Nigatu, Hellina Hailu and Thinwa, Cynthia and Louis, Lerato and Abdulmumin, Idris and Oyerinde, Samuel Gbenga and Ajibade, Benjamin Ayoade and Zhou, Helper and Onwuegbuzia, Emeka Felix and Emezue, Handel Chiagozie and Ige, Ifeoluwatayo Adeseye and Tonja, Atnafu Lambebo and Chukwuneke, Chiamaka Ijeoma and Muhammad, Shamsuddeen Hassan and Samuel, Olanrewaju},
  booktitle = {3rd Workshop on African Natural Language Processing},
  year = {2022},
  url = {https://openreview.net/forum?id=B0GEqcGV8-5}
}

WiNLP

Domain-Specific Lexicon-Based Sentiment Analysis using Contextual Shifter Patterns

Shamsuddeen Muhammad, Pavel Brazdil, and Idris Abdulmumin

In Proceedings of the Sixth Workshop on Widening Natural Language Processing, Dec 2022

Bib

@inproceedings{muhammad-2022-domain,
  title = {Domain-Specific Lexicon-Based Sentiment Analysis using Contextual Shifter Patterns},
  author = {Muhammad, Shamsuddeen and Brazdil, Pavel and Abdulmumin, Idris},
  booktitle = {Proceedings of the Sixth Workshop on Widening Natural Language Processing},
  month = dec,
  year = {2022},
  address = {Abu Dhabi, United Arab Emirates},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2022.winlp-1.0}
}

WiNLP

HERDPhobia: A Dataset for Hate Speech Detection against Fulani Herdsmen in Nigeria

Saminu Aliyu, Gregory Wajiga, Muhammad Murtala, and 3 more authors

In Proceedings of the Sixth Workshop on Widening Natural Language Processing, Dec 2022

Bib

@inproceedings{aliyu-2022-herdphobia,
  title = {HERDPhobia: A Dataset for Hate Speech Detection against Fulani Herdsmen in Nigeria},
  author = {Aliyu, Saminu and Wajiga, Gregory and Murtala, Muhammad and Muhammad, Shamsuddeen and Abdulmumin, Idris and Ahmad, Ibrahim},
  booktitle = {Proceedings of the Sixth Workshop on Widening Natural Language Processing},
  month = dec,
  year = {2022},
  address = {Abu Dhabi, United Arab Emirates},
  publisher = {Association for Computational Linguistics},
  url = {https://arxiv.org/abs/2211.15262}
}

EMNLP

MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition

David Ifeoluwa Adelani, Graham Neubig, Sebastian Ruder, and 42 more authors

In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, Dec 2022

Bib

@inproceedings{adelani-2022-masakhaner,
  url = {https://aclanthology.org/2022.emnlp-main.298},
  author = {Adelani, David Ifeoluwa and Neubig, Graham and Ruder, Sebastian and Rijhwani, Shruti and Beukman, Michael and Palen-Michel, Chester and Lignos, Constantine and Alabi, Jesujoba O. and Muhammad, Shamsuddeen H. and Nabende, Peter and Dione, Cheikh M. Bamba and Bukula, Andiswa and Mabuya, Rooweither and Dossou, Bonaventure F. P. and Sibanda, Blessing and Buzaaba, Happy and Mukiibi, Jonathan and Kalipe, Godson and Mbaye, Derguene and Taylor, Amelia and Kabore, Fatoumata and Emezue, Chris Chinenye and Aremu, Anuoluwapo and Ogayo, Perez and Gitau, Catherine and Munkoh-Buabeng, Edwin and Koagne, Victoire M. and Tapo, Allahsera Auguste and Macucwa, Tebogo and Marivate, Vukosi and Mboning, Elvis and Gwadabe, Tajuddeen and Adewumi, Tosin and Ahia, Orevaoghene and Nakatumba-Nabende, Joyce and Mokono, Neo L. and Ezeani, Ignatius and Chukwuneke, Chiamaka and Adeyemi, Mofetoluwa and Hacheme, Gilles Q. and Abdulmumin, Idris and Ogundepo, Odunayo and Yousuf, Oreen and Ngoli, Tatiana Moteu and Klakow, Dietrich},
  title = {{MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition}},
  booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing},
  month = dec,
  year = {2022},
  address = {Abu Dhabi, United Arab Emirates},
  publisher = {Association for Computational Linguistics},
  pages = {4488--4508}
}

IEEE

Quantity vs. Quality of Monolingual Source Data in Automatic Text Translation: Can It Be Too Little If It Is Too Good?

Idris Abdulmumin, Bashir Shehu Galadanci, Shamsuddeen Hassan Muhammad, and 1 more author

In 2022 IEEE Nigeria 4th International Conference on Disruptive Technologies for Sustainable Development (NIGERCON), Dec 2022

DOI Bib

@inproceedings{9803137,
  author = {Abdulmumin, Idris and Galadanci, Bashir Shehu and Hassan Muhammad, Shamsuddeen and Aliyu, Garba},
  booktitle = {2022 IEEE Nigeria 4th International Conference on Disruptive Technologies for Sustainable Development (NIGERCON)},
  title = {Quantity vs. Quality of Monolingual Source Data in Automatic Text Translation: Can It Be Too Little If It Is Too Good?},
  year = {2022},
  volume = {},
  number = {},
  pages = {1-5},
  doi = {10.1109/NIGERCON54645.2022.9803137}
}

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}
}

WMT

Separating Grains from the Chaff: Using Data Filtering to Improve Multilingual Translation for Low-Resourced African Languages

Idris Abdulmumin, Michael Beukman, Jesujoba Alabi, and 8 more authors

In Proceedings of the Seventh Conference on Machine Translation, Dec 2022

Bib

@inproceedings{abdulmumin-EtAl:2022:WMT,
  author = {Abdulmumin, Idris and Beukman, Michael and Alabi, Jesujoba and Emezue, Chris Chinenye and Chimoto, Everlyn and Adewumi, Tosin and Muhammad, Shamsuddeen and Adeyemi, Mofetoluwa and Yousuf, Oreen and Singh, Sahib and Gwadabe, Tajuddeen},
  title = {Separating Grains from the Chaff: Using Data Filtering to Improve Multilingual Translation for Low-Resourced African Languages},
  booktitle = {Proceedings of the Seventh Conference on Machine Translation},
  month = dec,
  year = {2022},
  address = {Abu Dhabi},
  publisher = {Association for Computational Linguistics},
  pages = {1001--1014}
}

arXiv

BLOOM: A 176B-Parameter Open-Access Multilingual Language Model

Teven Le Scao, Angela Fan, Christopher Akiki, and 387 more authors

Dec 2022

DOI Bib

@misc{https://doi.org/10.48550/arxiv.2211.05100,
  doi = {10.48550/ARXIV.2211.05100},
  url = {https://arxiv.org/abs/2211.05100},
  author = {Scao, Teven Le and Fan, Angela and Akiki, Christopher and Pavlick, Ellie and Ilić, Suzana and Hesslow, Daniel and Castagné, Roman and Luccioni, Alexandra Sasha and Yvon, François and Gallé, Matthias and Tow, Jonathan and Rush, Alexander M. and Biderman, Stella and Webson, Albert and Ammanamanchi, Pawan Sasanka and Wang, Thomas and Sagot, Benoît and Muennighoff, Niklas and del Moral, Albert Villanova and Ruwase, Olatunji and Bawden, Rachel and Bekman, Stas and McMillan-Major, Angelina and Beltagy, Iz and Nguyen, Huu and Saulnier, Lucile and Tan, Samson and Suarez, Pedro Ortiz and Sanh, Victor and Laurençon, Hugo and Jernite, Yacine and Launay, Julien and Mitchell, Margaret and Raffel, Colin and Gokaslan, Aaron and Simhi, Adi and Soroa, Aitor and Aji, Alham Fikri and Alfassy, Amit and Rogers, Anna and Nitzav, Ariel Kreisberg and Xu, Canwen and Mou, Chenghao and Emezue, Chris and Klamm, Christopher and Leong, Colin and van Strien, Daniel and Adelani, David Ifeoluwa and Radev, Dragomir and Ponferrada, Eduardo González and Levkovizh, Efrat and Kim, Ethan and Natan, Eyal Bar and De Toni, Francesco and Dupont, Gérard and Kruszewski, Germán and Pistilli, Giada and Elsahar, Hady and Benyamina, Hamza and Tran, Hieu and Yu, Ian and Abdulmumin, Idris and Johnson, Isaac and Gonzalez-Dios, Itziar and de la Rosa, Javier and Chim, Jenny and Dodge, Jesse and Zhu, Jian and Chang, Jonathan and Frohberg, Jörg and Tobing, Joseph and Bhattacharjee, Joydeep and Almubarak, Khalid and Chen, Kimbo and Lo, Kyle and Von Werra, Leandro and Weber, Leon and Phan, Long and allal, Loubna Ben and Tanguy, Ludovic and Dey, Manan and Muñoz, Manuel Romero and Masoud, Maraim and Grandury, María and Šaško, Mario and Huang, Max and Coavoux, Maximin and Singh, Mayank and Jiang, Mike Tian-Jian and Vu, Minh Chien and Jauhar, Mohammad A. and Ghaleb, Mustafa and Subramani, Nishant and Kassner, Nora and Khamis, Nurulaqilla and Nguyen, Olivier and Espejel, Omar and de Gibert, Ona and Villegas, Paulo and Henderson, Peter and Colombo, Pierre and Amuok, Priscilla and Lhoest, Quentin and Harliman, Rheza and Bommasani, Rishi and López, Roberto Luis and Ribeiro, Rui and Osei, Salomey and Pyysalo, Sampo and Nagel, Sebastian and Bose, Shamik and Muhammad, Shamsuddeen Hassan and Sharma, Shanya and Longpre, Shayne and Nikpoor, Somaieh and Silberberg, Stanislav and Pai, Suhas and Zink, Sydney and Torrent, Tiago Timponi and Schick, Timo and Thrush, Tristan and Danchev, Valentin and Nikoulina, Vassilina and Laippala, Veronika and Lepercq, Violette and Prabhu, Vrinda and Alyafeai, Zaid and Talat, Zeerak and Raja, Arun and Heinzerling, Benjamin and Si, Chenglei and Salesky, Elizabeth and Mielke, Sabrina J. and Lee, Wilson Y. and Sharma, Abheesht and Santilli, Andrea and Chaffin, Antoine and Stiegler, Arnaud and Datta, Debajyoti and Szczechla, Eliza and Chhablani, Gunjan and Wang, Han and Pandey, Harshit and Strobelt, Hendrik and Fries, Jason Alan and Rozen, Jos and Gao, Leo and Sutawika, Lintang and Bari, M Saiful and Al-shaibani, Maged S. and Manica, Matteo and Nayak, Nihal and Teehan, Ryan and Albanie, Samuel and Shen, Sheng and Ben-David, Srulik and Bach, Stephen H. and Kim, Taewoon and Bers, Tali and Fevry, Thibault and Neeraj, Trishala and Thakker, Urmish and Raunak, Vikas and Tang, Xiangru and Yong, Zheng-Xin and Sun, Zhiqing and Brody, Shaked and Uri, Yallow and Tojarieh, Hadar and Roberts, Adam and Chung, Hyung Won and Tae, Jaesung and Phang, Jason and Press, Ofir and Li, Conglong and Narayanan, Deepak and Bourfoune, Hatim and Casper, Jared and Rasley, Jeff and Ryabinin, Max and Mishra, Mayank and Zhang, Minjia and Shoeybi, Mohammad and Peyrounette, Myriam and Patry, Nicolas and Tazi, Nouamane and Sanseviero, Omar and von Platen, Patrick and Cornette, Pierre and Lavallée, Pierre François and Lacroix, Rémi and Rajbhandari, Samyam and Gandhi, Sanchit and Smith, Shaden and Requena, Stéphane and Patil, Suraj and Dettmers, Tim and Baruwa, Ahmed and Singh, Amanpreet and Cheveleva, Anastasia and Ligozat, Anne-Laure and Subramonian, Arjun and Névéol, Aurélie and Lovering, Charles and Garrette, Dan and Tunuguntla, Deepak and Reiter, Ehud and Taktasheva, Ekaterina and Voloshina, Ekaterina and Bogdanov, Eli and Winata, Genta Indra and Schoelkopf, Hailey and Kalo, Jan-Christoph and Novikova, Jekaterina and Forde, Jessica Zosa and Clive, Jordan and Kasai, Jungo and Kawamura, Ken and Hazan, Liam and Carpuat, Marine and Clinciu, Miruna and Kim, Najoung and Cheng, Newton and Serikov, Oleg and Antverg, Omer and van der Wal, Oskar and Zhang, Rui and Zhang, Ruochen and Gehrmann, Sebastian and Pais, Shani and Shavrina, Tatiana and Scialom, Thomas and Yun, Tian and Limisiewicz, Tomasz and Rieser, Verena and Protasov, Vitaly and Mikhailov, Vladislav and Pruksachatkun, Yada and Belinkov, Yonatan and Bamberger, Zachary and Kasner, Zdeněk and Rueda, Alice and Pestana, Amanda and Feizpour, Amir and Khan, Ammar and Faranak, Amy and Santos, Ana and Hevia, Anthony and Unldreaj, Antigona and Aghagol, Arash and Abdollahi, Arezoo and Tammour, Aycha and HajiHosseini, Azadeh and Behroozi, Bahareh and Ajibade, Benjamin and Saxena, Bharat and Ferrandis, Carlos Muñoz and Contractor, Danish and Lansky, David and David, Davis and Kiela, Douwe and Nguyen, Duong A. and Tan, Edward and Baylor, Emi and Ozoani, Ezinwanne and Mirza, Fatima and Ononiwu, Frankline and Rezanejad, Habib and Jones, Hessie and Bhattacharya, Indrani and Solaiman, Irene and Sedenko, Irina and Nejadgholi, Isar and Passmore, Jesse and Seltzer, Josh and Sanz, Julio Bonis and Fort, Karen and Dutra, Livia and Samagaio, Mairon and Elbadri, Maraim and Mieskes, Margot and Gerchick, Marissa and Akinlolu, Martha and McKenna, Michael and Qiu, Mike and Ghauri, Muhammed and Burynok, Mykola and Abrar, Nafis and Rajani, Nazneen and Elkott, Nour and Fahmy, Nour and Samuel, Olanrewaju and An, Ran and Kromann, Rasmus and Hao, Ryan and Alizadeh, Samira and Shubber, Sarmad and Wang, Silas and Roy, Sourav and Viguier, Sylvain and Le, Thanh and Oyebade, Tobi and Le, Trieu and Yang, Yoyo and Nguyen, Zach and Kashyap, Abhinav Ramesh and Palasciano, Alfredo and Callahan, Alison and Shukla, Anima and Miranda-Escalada, Antonio and Singh, Ayush and Beilharz, Benjamin and Wang, Bo and Brito, Caio and Zhou, Chenxi and Jain, Chirag and Xu, Chuxin and Fourrier, Clémentine and Periñán, Daniel León and Molano, Daniel and Yu, Dian and Manjavacas, Enrique and Barth, Fabio and Fuhrimann, Florian and Altay, Gabriel and Bayrak, Giyaseddin and Burns, Gully and Vrabec, Helena U. and Bello, Imane and Dash, Ishani and Kang, Jihyun and Giorgi, John and Golde, Jonas and Posada, Jose David and Sivaraman, Karthik Rangasai and Bulchandani, Lokesh and Liu, Lu and Shinzato, Luisa and de Bykhovetz, Madeleine Hahn and Takeuchi, Maiko and Pàmies, Marc and Castillo, Maria A and Nezhurina, Marianna and Sänger, Mario and Samwald, Matthias and Cullan, Michael and Weinberg, Michael and De Wolf, Michiel and Mihaljcic, Mina and Liu, Minna and Freidank, Moritz and Kang, Myungsun and Seelam, Natasha and Dahlberg, Nathan and Broad, Nicholas Michio and Muellner, Nikolaus and Fung, Pascale and Haller, Patrick and Chandrasekhar, Ramya and Eisenberg, Renata and Martin, Robert and Canalli, Rodrigo and Su, Rosaline and Su, Ruisi and Cahyawijaya, Samuel and Garda, Samuele and Deshmukh, Shlok S and Mishra, Shubhanshu and Kiblawi, Sid and Ott, Simon and Sang-aroonsiri, Sinee and Kumar, Srishti and Schweter, Stefan and Bharati, Sushil and Laud, Tanmay and Gigant, Théo and Kainuma, Tomoya and Kusa, Wojciech and Labrak, Yanis and Bajaj, Yash Shailesh and Venkatraman, Yash and Xu, Yifan and Xu, Yingxin and Xu, Yu and Tan, Zhe and Xie, Zhongli and Ye, Zifan and Bras, Mathilde and Belkada, Younes and Wolf, Thomas},
  title = {{BLOOM: A 176B-Parameter Open-Access Multilingual Language Model}},
  publisher = {arXiv},
  year = {2022}
}

2021

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}
}

IAENG EL

A hybrid approach for improved low resource neural machine translation using monolingual data

Idris Abdulmumin, Bashir Shehu Galadanci, Abubakar Isah, and 2 more authors

Engineering Letters, Nov 2021

Bib

@article{Abdulmumin2021-hybrid-eng-letters,
  title = {A hybrid approach for improved low resource neural machine translation using monolingual data},
  journal = {Engineering Letters},
  year = {2021},
  month = nov,
  volume = {29},
  number = {4},
  pages = {1478--1493},
  author = {Abdulmumin, Idris and Galadanci, Bashir Shehu and Isah, Abubakar and Kakudi, Habeebah Adamu and Sinan, Isma'ila Idris}
}

LNCS

Data Selection as an Alternative to Quality Estimation in Self-Learning for Low Resource Neural Machine Translation

Idris Abdulmumin, Bashir Shehu Galadanci, Ibrahim Said Ahmad, and 1 more author

In Computational Science and Its Applications – ICCSA 2021, Nov 2021

DOI Bib

@incollection{Abdulmumin2021c,
  author = {Abdulmumin, Idris and Galadanci, Bashir Shehu and Ahmad, Ibrahim Said and Abdullahi, Rabiu Ibrahim},
  editor = {Gervasi, Osvaldo and Murgante, Beniamino and Misra, Sanjay and Garau, Chiara and Ble{\v{c}}i{\'{c}}, Ivan and Taniar, David and Apduhan, Bernady O. and Rocha, Ana Maria A. C. and Tarantino, Eufemia and Torre, Carmelo Maria},
  title = {Data Selection as an Alternative to Quality Estimation in Self-Learning for Low Resource Neural Machine Translation},
  booktitle = {Computational Science and Its Applications -- ICCSA 2021},
  year = {2021},
  publisher = {Springer International Publishing},
  address = {Cham},
  pages = {311--326},
  isbn = {978-3-030-87013-3},
  doi = {10.1007/978-3-030-87013-3_24},
  url = {http://doi.org/10.1007/978-3-030-87013-3_24}
}

CCIS

Enhanced Back-Translation for Low Resource Neural Machine Translation Using Self-training

Idris Abdulmumin, Bashir Shehu Galadanci, and Abubakar Isa

In Information and Communication Technology and Applications, Nov 2021

DOI Bib

@incollection{10.1007/978-3-030-69143-1_28,
  author = {Abdulmumin, Idris and Galadanci, Bashir Shehu and Isa, Abubakar},
  editor = {Misra, Sanjay and Muhammad-Bello, Bilkisu},
  title = {Enhanced Back-Translation for Low Resource Neural Machine Translation Using Self-training},
  booktitle = {Information and Communication Technology and Applications},
  year = {2021},
  publisher = {Springer International Publishing},
  address = {Cham},
  pages = {355--371},
  isbn = {978-3-030-69143-1},
  doi = {10.1007/978-3-030-69143-1_28}
}

2019

IEEE

HauWE: Hausa Words Embedding for Natural Language Processing

Idris Abdulmumin and Bashir Shehu Galadanci

In 2019 2nd International Conference of the IEEE Nigeria Computer Chapter, NigeriaComputConf 2019, Nov 2019

Bib

@inproceedings{Abdulmumin2019,
  title = {HauWE: Hausa Words Embedding for Natural Language Processing},
  booktitle = {2019 2nd International Conference of the IEEE Nigeria Computer Chapter, NigeriaComputConf 2019},
  year = {2019},
  author = {Abdulmumin, Idris and Galadanci, Bashir Shehu},
  url = {http://ieeexplore.ieee.org/document/8949674/},
  address = {Zaria, Kaduna-Nigeria}
}