Instrument Acquisition for Endangered Languages Research: Development of an Ontology-based Toolbox

Wayne State University, Detroit MI

Investigators

Abstract

This project, addressing endangered language research, develops digital archiving infrastructure, as well as digital tools for use by individual linguists. Half of the world's approximately 7000 languages are expected to disappear during the century. This project records speakers in their cultural setting to preserve an understanding of their society. Language goes beyond serving as just a tool for members of a culture, serving as the essential vehicle through which all experience is interpreted, and the medium by which we understand the world we live in. The work digitizes, archives, and analyzes linguistic data to make it accessible, searchable, and interpretable to future generations and encourages not only the preservation of existing digital language documentation but also their creation and analysis. The infrastructure acquired will service the following goals: - Immediate development of a web portal for endangered languages that will eventually allow access to all language and cultural data in general, - Training and matriculation of students in language engineering and linguistics, and - Community outreach. The research is expected to create the first tool- and data-rich online web portal dedicated to preserving and providing access to documentation of endangered languages, developing tools for data integration, cross-language querying and linguistic analysis. The portal will support interdisciplinary research in ontology, data integration, multimedia data management, language engineering, and security. Broader Impact: The project will facilitate the fusion of several disciplines within computer science and the arts and humanities with a single application focus. It will also contribute in establishing a multi-institutional doctoral degree and a graduate student certificate program in Language Engineering. Moreover, the portal will provide outreach support for field linguistics, serving as a source for students at all levels on minority languages and cultures, especially those that have been or are endangered.