Tadesse Destaw Belay
I'm a Natural Language Processing researcher focusing on low-resource African languages at the University of Hamburg. My work focuses on developing NLP tools, datasets, and models for African languages.
My research interests include multilingual language models, machine translation, and social NLP. I have contributed to several pioneering projects including AfriHate - a multilingual collection of hate speech datasets for African languages, EthioLLM - large language models for Ethiopian languages, and EthioEmo - a multi-label emotion classification dataset. I'm particularly interested in addressing the unique challenges of low-resource languages through innovative data collection, annotation, and modeling approaches.
I've published extensively in major NLP conferences like EMNLP, LREC, and RANLP. My work aims to bridge the technological gap for African languages by developing foundational resources and tools while exploring important considerations like gender bias, dialectal variations, and cultural context in NLP systems. I collaborate actively with researchers across institutions to advance NLP capabilities for Ethiopian and other African languages.
Publications
AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages
Shamsuddeen Hassan Muhammad, Idris Abdulmumin, A. Ayele, David Ifeoluwa Adelani, Ibrahim Said Ahmad, Saminu Mohammad Aliyu, Nelson Odhiambo Onyango, Lilian D. A. Wanzare, Samuel Rutunda, L. J. Aliyu, E. Alemneh, Oumaima Hourrane, Hagos Tesfahun Gebremichael, Elyas Abdi Ismail, Meriem Beloucif, Ebrahim Chekol Jibril, Andiswa Bukula, Rooweither Mabuya, Salomey Osei, Abigail Oppong, Tadesse Destaw Belay, Tadesse Kebede Guge, T. Asfaw, C. Chukwuneke, Paul Rottger, Seid Muhie Yimam, N. Ousidhoum
ProverbEval: Exploring LLM Evaluation Challenges for Low-resource Language Understanding
Israel Abebe Azime, A. Tonja, Tadesse Destaw Belay, Yonas Chanie, Bontu Fufa Balcha, Negasi Haile Abadi, Henok Biadglign Ademtew, Mulubrhan Abebe Nerea, D. Yadeta, Derartu Dagne Geremew, Assefa Atsbiha tesfau, Philipp Slusallek, T. Solorio, D. Klakow
arXiv.org 2024
EthioLLM: Multilingual Large Language Models for Ethiopian Languages with Task Evaluation
A. Tonja, Israel Abebe Azime, Tadesse Destaw Belay, M. Yigezu, Moges Ahmed Mehamed, A. Ayele, Ebrahim Chekol Jibril, Michael Melese Woldeyohannis, Olga Kolesnikova, Philipp Slusallek, D. Klakow, Shengwu Xiong, Seid Muhie Yimam
International Conference on Language Resources and Evaluation 2024
Walia-LLM: Enhancing Amharic-LLaMA by Integrating Task-Specific and Generative Datasets
Israel Abebe Azime, Mitiku Yohannes Fuge, A. Tonja, Tadesse Destaw Belay, A. Wassie, Eyasu Shiferaw Jada, Yonas Chanie, W. Sewunetie, Seid Muhie Yimam
Conference on Empirical Methods in Natural Language Processing 2024
AfriSenti: A Twitter Sentiment Analysis Benchmark for African Languages
Shamsuddeen Hassan Muhammad, Idris Abdulmumin, A. Ayele, N. Ousidhoum, David Ifeoluwa Adelani, Seid Muhie Yimam, I. Ahmad, Meriem Beloucif, Saif M. Mohammad, Sebastian Ruder, Oumaima Hourrane, P. Brazdil, Felermino D'ario M'ario Ant'onio Ali, Davis C. Davis, Salomey Osei, Bello Shehu Bello, Falalu Ibrahim, T. Gwadabe, Samuel Rutunda, Tadesse Destaw Belay, Wendimu Baye Messelle, Hailu Beshada Balcha, S. Chala, Hagos Tesfahun Gebremichael, Bernard Opoku, Steven Arthur
Conference on Empirical Methods in Natural Language Processing 2023
Mining Road Traffic Accident Data for Prediction of Accident Severity
Tadesse Kebede Bahiru, V. Manjula, Tadesse Birara Akele, Engdaw Ayalew Tesfaw, Tadesse Destaw Belay
2023 International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT) 2023
Dialect-Based Noisy Speech Dataset, Pre-Processing Tools, and Recognition Models for Amharic
Tesfa Tegegne Assfaw, T. Abebe, Belisty Yalew, Tadesse Destaw Belay
EAI International Conference on ICT for Development for Africa 2022
The 5Js in Ethiopia: Amharic Hate Speech Data Annotation Using Toloka Crowdsourcing Platform
A. Ayele, Skadi Dinter, Tadesse Destaw Belay, T. Asfaw, Seid Muhie Yimam, Chris Biemann
EAI International Conference on ICT for Development for Africa 2022
Impacts of Homophone Normalization on Semantic Models for Amharic
Tadesse Destaw Belay, A. Ayele, G. Gelaye, Seid Muhie Yimam, Chris Biemann
EAI International Conference on ICT for Development for Africa 2021
Gender Bias Evaluation in Machine Translation for Amharic, Tigrigna, and Afaan Oromoo
W. Sewunetie, A. Tonja, Tadesse Destaw Belay, H. Nigatu, Gashaw Gebremeskel, Zewdie Mossie, Hussien Seid, Seid Yimam
GITT 2024
A FRI S ENTI : A B ENCHMARK T WITTER S ENTIMENT A NALYSIS D ATASET FOR A FRICAN L ANGUAGES
Shamsuddeen Hassan Muhammad, Idris Abdulmumin, A. Ayele, N. Ousidhoum, David Ifeoluwa Adelani, Seid Muhie Yimam, Meriem Beloucif, Saif M. Mohammad, Sebastian Ruder, Oumaima Hourrane, P. Brazdil, Felermino M. D. A. Ali, Davis David, Salomey Osei, Bello Shehu Bello, Falalu Ibrahim, T. Gwadabe, Samuel Rutunda, Tadesse Destaw Belay, Wendimu Baye Messelle, Hailu Beshada Balcha, S. Chala, Hagos Tesfahun Gebremichael, Bernard Opoku, Steven Arthur
Emotion Classification for Amharic Social Media Text Comments Using Deep Learning
Sileshi Bogale Haile, Tadesse Destaw Belay, Tadesse Kebede Bahiru, Tadesse Birara Akele
Social Science Research Network 2022
Challenges of Amharic Hate Speech Data Annotation Using Yandex Toloka Crowdsourcing Platform
A. Ayele, Tadesse Destaw Belay, Seid Muhie Yimam, Skadi Dinter, T. Asfaw, Chris Biemann
Question Answering Classification for Amharic Social Media Community Based Questions
Tadesse Destaw Belay, Seid Muhie Yimam, A. Ayele, Chris Biemann
SIGUL 2022