Rochester Institute of Technology
NLP Crowdsourcing for Predominantly Oral Languages: The Case of Bambara
Abstract
dc:description.abstractPredominantly oral languages (POLs) face a significant "digital divide," as they are often excluded from the benefits of modern natural language processing (NLP) technologies, due to a lack of extensive, readily available machine learning (ML) datasets. We investigate methods to overcome this data scarcity for Bambara, a Manding language, spoken primarily in Mali, with a rich oral tradition but limited digital presence. The research leverages crowdsourcing and community engagement to build high-quality ML ready dataset resources. Key contributions include methods for automatic speech recognition (ASR) and machine translation (MT) dataset collection and curation and for educational resource creation. Our findings demonstrate that while POLs, specifically Bambara, presents unique challenges, including annotation complexity and technological barriers, crowdsourcing offers a scalable and inclusive path for their computational preservation. By integrating cultural knowledge with modern machine learning, this dissertation provides a framework for making NLP more equitable and accessible to Bambara speakers.
Degree
thesis:*- Name thesis:degree_name
- Computing and Information Sciences (Ph.D.)
- Level thesis:degree_level
- Dissertation
- Discipline thesis:degree_discipline
- Computing and Information Sciences Ph.D, Department of
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Tapo, Allahsera Auguste
- Contributors dc:contributor
-
- Christopher Homan
Subjects
dc:subject × 6Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.rit.edu/theses/12636