Digitizing Tibeto-Burman Languages through Flex: Insights from Manipuri

Recent advances in language technology have demanded systematic documentation and digital corpus development for digitally marginalized languages (DML) such as Manipuri, a Tibeto-Burman language of Northeast India. This study explores how I use version 9.2.2 of FieldWorks Language Explorer (FLEx) to develop the dataset (Poudel, 2026). FLEx is a software for linguistic analysis that generates machine-readable datasets for Natural Language Processing (NLP), machine translation, and Artificial Intelligence (AI) applications. The study adopts a qualitative, corpus-based research design, using the linguistic analysis software FLEx, to document, annotate, and interlinearize three categories of Manipuri textual data: Chainarol, a sixteenth-century treatise on war; Ukhruldai, a contemporary fictional narrative; and a set of elicited sentences translated from Nepali. The FLEx-based corpus construction transforms textual materials into structured, searchable, and machine-readable resources. This approach contributes to the development of digital language infrastructure for digital corpus construction, lexicography, NLP, machine translation, and AI applications.