🧑‍🔬 Atnafu Lambebo Tonja

🏛️ Affiliations

🎓Instituto Politécnico NacionalMexico City · Mexico2022–2024 · 23 papersEducation 2022–2024 · PhD, Computer Science🎓University of Colorado Colorado SpringsColorado Springs · United States2023 · 3 papers🎓Wolaita Sodo UniversitySodo · Ethiopia2021–2022 · 3 papers🎓Mohamed bin Zayed University of Artificial IntelligenceAbu Dhabi · United Arab Emirates2025–2026 · 2 papersEmployment 2025–2026 · Postdoctoral Associate, Natural Language Processing🎓University College LondonLondon · United Kingdom2026–2028Employment 2026–2028 · Senior Research Fellow ( Google DeepMind Academic Fellow), Computer Science

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. MasakhaNEWS: News Topic Classification for African languages (2023 · 81 citations)
   African languages are spoken by about a fifth of humanity, yet they have few evaluation datasets. Most existing news topic resources cover single languages, use inconsistent label sets, or were labelled with little human oversight. MasakhaNEWS addresses this gap. It is a news topic classification benchmark for 16…
2. AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR (2023 · 45 citations)
   Speech recognition systems now reach near-human accuracy on standard English benchmarks. They still perform poorly on African-accented speech, and no public resource existed for clinical ASR on such accents. This gap matters for African clinicians, who face heavy patient loads and could benefit from dictation tools.…
3. Walia-LLM: Enhancing Amharic-LLaMA by Integrating Task-Specific and Generative Datasets (2024 · 11 citations)
   Open LLMs such as LLaMA-2 were barely exposed to Amharic during pre-training. The existing adaptation, LLaMA-2-Amharic (Andersland, 2024), was instruction-tuned only on English instructions that had been machine-translated into Amharic. The authors ask whether native Amharic supervision can do better. They reuse…
4. CommonLID: Re-evaluating State-of-the-Art Language Identification Performance on Web Data (2026 · 3 citations)
   Language identification (LID) is often treated as a solved task. In practice, it remains unreliable for many languages on noisy, mixed web text, which is the main source of multilingual pre-training corpora. Most existing benchmarks, such as FLORES, UDHR and Bible data, are clean, translated or religious, so they…
5. A Case Against Implicit Standards: Homophone Normalization in Machine Translation for Languages that use the Ge'ez Script. (2025 · 2 citations)
   Amharic NLP work often applies homophone normalization as a routine cleanup step. This step collapses Ge'ez-script characters that sound alike in Amharic into one character, which raises exact-match metrics such as BLEU. The authors argue that this habit quietly sets a standard for every language written in the…
6. Afri-MCQA: Multimodal Cultural Question Answering for African Languages (2026)
   Afri-MCQA addresses a gap in multimodal AI evaluation. Existing cultural VQA benchmarks cover few African languages and query models only through text, even though many African languages are used mainly in spoken form. The authors built a benchmark of about 7.5k image-grounded question–answer pairs in 15 sub-Saharan…

All works

7 works of theirs in our library, the most cited first; 6 with a page here, the others link their original until we summarise them.

1. MasakhaNEWS: News Topic Classification for African languagesInternational Joint Conference on Natural Language Processing (IJCNLP)David Ifeoluwa Adelani, Marek Masiak, Israel Abebe Azime, et al.2023 · 81 citations
2. AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASRTransactions of the Association for Computational Linguistics (TACL)Tobi Olatunji, Tejumade Afonja, Aditya Yadavalli, et al.2023 · 45 citations
3. Walia-LLM: Enhancing Amharic-LLaMA by Integrating Task-Specific and Generative DatasetsFindings of the Association for Computational LinguisticsIsrael Abebe Azime, Atnafu Lambebo Tonja, Tadesse Destaw Belay, et al.2024 · 11 citations
4. CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation ↗Findings of the Association for Computational Linguistics: EMNLP 2025 · no summary yetEmilio Villa-Cueva et al.2025 · 5 citations
5. CommonLID: Re-evaluating State-of-the-Art Language Identification Performance on Web DataAnnual Meeting of the Association for Computational Linguistics (ACL)Pedro Ortiz Suarez, Laurie Burchell, Catherine Arnett, et al.2026 · 3 citations
6. A Case Against Implicit Standards: Homophone Normalization in Machine Translation for Languages that use the Ge'ez Script.Conference on Empirical Methods in Natural Language Processing (EMNLP)Hellina Hailu Nigatu, Atnafu Lambebo Tonja, Henok Biadglign Ademtew, et al.2025 · 2 citations
7. Afri-MCQA: Multimodal Cultural Question Answering for African LanguagesAnnual Meeting of the Association for Computational Linguistics (ACL)Atnafu Lambebo Tonja, Srija Anand, Emilio Villa-Cueva, et al.2026

🤝 Co-authors here

12 of 26 co-authors with a page, the most papers together first.

• Israel Abebe Azime ×3
• Bonaventure F. P. Dossou ×2
• Chris Chinenye Emezue ×2
• Idris Abdulmumin ×2
• Jesujoba Alabi ×2
• Naome A Etori ×2
• Negasi Haile Abadi ×2
• Seid Muhie Yimam ×2
• Tadesse Destaw Belay ×2
• Aditya Yadavalli
• Aman Kassahun Wassie
• Catherine Arnett

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×2: ACL 2026 ×2
• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2025
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2024
• International Joint Conference on Natural Language Processing (IJCNLP): IJCNLP 2023
• Transactions of the Association for Computational Linguistics (TACL): Transactions of the Association for Computational Linguistics (TACL) 2023
• Findings of the Association for Computational Linguistics: EMNLP 2025

🔗 Cited by

Papers of our library cite their works 110 times (of the 149,439 papers whose bibliographies we read); 32 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/atnafu-lambebo-tonja/