CV

Education

• B.S. in Computer Science, African Leadership University, 2021
• M.S. in Language Technologies, Carnegie Mellon University, 2023 (expected)

Work experience

• Summer 2021: Engineering Summer Analyst
  • Goldman Sachs
  • Duties included: Coding in Java
  • Supervisor: Kelvin Deville

Skills

• Python
• NLP
  • Machine Translation(learning)
  • Speech recognition (learning)
  • multi-lingual NLP (learning)
• Java

Projects

• AfricanVoices : We collect, build and share text-to-speech datasets and synthesizers for African languages.
• Lacuna NER/POS (June 2021 - Present): Building POS and NER datasets for African languages. Language cordinator for Luo.
• BlackAIR research grant recepient(June 2021-August 2021: Built Luo-English parallel dataset

Publications

MasakhaNER: Named Entity Recognition for African Languages

Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages

Quality-Aware Decoding for Neural Machine Translation

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

BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus

Building African Voices

When Is TTS Augmentation Through a Pivot Language Useful?

Talks

Podcast on Masakhane and Participatory Research for African Languages

April 01, 2021

Podcast at Allen AI NLP highlights podcast, Remote

Talk on MasakhaNER and Participatory Research

October 04, 2021

Talk at Google NLP Reading group, Remote

Building African Voices

November 10, 2021

Panels at SustaiNLP2021 at EMNLP, Remote

AfricaNLP workshop panel

April 25, 2022

Panel at ICLR 2022 -Africanlp workshop, Remote

Supporting Linguistic Diversity

May 22, 2022

Panels at ACL 2022, Remote/In person

Building African Voices

August 01, 2022

Talk at LANFRICA, Remote

Service and leadership

• Researcher at Masakhane focusing on NLP for Luo
• Co-organiser of AfricaNLP2022 workshop colocated at ICLR 2022.