Septemper 2023
Welcome to the Septemper 2023 edition of the FormosanBank newsletter! Here, we recap key achievements from the first months of our project, as we laid the groundwork for creating a machine-readable corpus of the Indigenous Formosan languages.
Securing Funding We are thrilled to announce a 3-year grant from the U.S. National Science Foundation, which enables us to hire staff and conduct essential research trips. This support will accelerate our efforts to build and expand the FormosanBank corpus.
Resource Assessment Our team has cataloged existing resources and obtained permissions for essential materials, including dictionaries, corpora, and audio recordings. This step has brought us closer to compiling the largest machine-readable collection of endangered languages.
Example Sentence Extraction We extracted thousands of example sentences from 16 electronic dictionaries, creating a valuable parallel corpus for future machine learning applications. This work forms a strong foundation for our ongoing data processing and analysis efforts.
For a comprehensive view of our early achievements, please refer to the full September 2023 newsletter PDFs below:
Last updated