Project Grant 2319246
- This National Science Foundation (NSF) Computer and Information Science and Engineering (CFDA 47.070) Project Grant awarded to the University of Arizona, doing business as the Arizona Board of Regents, will develop five new Universal Dependencies (UD) corpora of endangered languages totaling at least 30,000 tokens each. The $139,306 award, spanning August 2023 to July 2026, will produce: (1) freely-available, fully-annotated treebanks for quantitative linguistic analyses and natural language...
- This National Science Foundation (NSF) Project Grant, awarded under the Social, Behavioral, and Economic Sciences program (CFDA 47.075), provides $457,997 to Indiana University to build a 1.4-million-word syntactically parsed electronic corpus spanning 900 years of a single language. The corpus will allow researchers to investigate grammatical change and variation over time, as well as enable comparisons to similar developments in related languages. The project involves manual annotation of...
- This $285,326 Project Grant awarded by the National Science Foundation's (NSF) Social, Behavioral, and Economic Sciences (CFDA 47.075) program funds a 3-year community-driven documentation project focused on critically endangered, rarely studied, and infrequently documented languages. The project aims to produce transcribed and translated narratives in an open-access, permanently archived collection, develop a research-enriched, community-based interactive multimedia learning site, and conduct...
- The Endangered Language Fund, Inc. received a $251,929 project grant award from the National Science Foundation's Social, Behavioral, and Economic Sciences program (CFDA 47.075) to develop an indigenous language database project. Through this three-year award ending in August 2026, the Endangered Language Fund will compile invaluable language resources for an endangered Native American language. These include a grammar, dictionary, collection of oral literature translated and analyzed, and...
- This $116,797 federal Project Grant award from the National Science Foundation's (NSF) Social, Behavioral, and Economic Sciences (CFDA 47.075) program supports research to document, analyze, and revitalize a contact language that has undergone significant grammatical change. The project will record 40 hours of natural speech through sociolinguistic interviews and linguistic elicitation, transcribe and annotate the data, and develop an open-access digital corpus. Grounded in theories of...
- This $296,804 EAGER grant awarded by the National Science Foundation's (NSF) Social, Behavioral, and Economic Sciences (CFDA 47.075) program will support the development of new natural language processing tools and language models for an endangered language. The project at the University of Hawaii at Manoa will first collect and consolidate language data, then train machine translation systems to translate text both into and out of the endangered language. The project will also investigate...
- This Project Grant award from the National Science Foundation's (NSF) Social, Behavioral, and Economic Sciences (CFDA 47.075) program provides $391,927 to document the morphologically complex endangered language spoken by elders in a community where it is in contact with another indigenous language. The key objectives are to create a digital corpus capturing the naturalistic use of the endangered language by fluent elder speakers and to analyze the language's directional systems expressed...
- This National Science Foundation (NSF) Project Grant award under the Social, Behavioral, and Economic Sciences (CFDA 47.075) program provides $268,067 to The Research Foundation For The State University Of New York (RF SUNY) to advance linguistic research through the development of speech technologies. The key products and services delivered under this 2-year award, which runs from August 1, 2025 to July 31, 2027, include: Creation of benchmark datasets, comprehensive lexica, and advanced data...
- This Project Grant award from the National Science Foundation Division of Behavioral and Cognitive Sciences provides $449,712 to the University of Georgia Research Foundation to document and analyze endangered language varieties spoken in a linguistically diverse border region as part of the NSF Dynamic Language Infrastructure - NEH Documenting Endangered Languages program (CFDA 47.075, Social, Behavioral, and Economic Sciences). The award period is from September 1, 2022 to August 31, 2025....
- The National Science Foundation (NSF) awarded a $354,310 CAREER grant to Trustees of Indiana University, doing business as Indiana University, to build a digital phonological atlas charting the linguistic structures of an extensively used yet underexplored spoken language variety. The project, funded under NSF's Social, Behavioral, and Economic Sciences (CFDA 47.075) program, will investigate how speech evolves over time and across different regions through linguistic interviews with 160...
This National Science Foundation (NSF) award under the Computer and Information Science and Engineering program (CFDA 47.070) provides $299,977 to Trustees of Indiana University to develop five new syntactically-annotated corpora of endangered languages. The project aims to build high-quality datasets and computational tools for analyzing the grammars of these languages, validating new techniques that can work with small datasets. The key products include: (1) five freely-available treebanks of at least 30,000 tokens each, (2) open-source natural language processing pipeline models for word segmentation, stemming, morphological analysis, and syntactic parsing of the target languages, (3) novel methods for identifying areal linguistic clusters and leveraging this information to bootstrap NLP systems for related languages, and (4) a thematic volume describing comparative syntactic investigations using the collected corpora. This award supports the NSF's mission to advance the development and use of research cyberinfrastructure that can enable discovery and innovation, particularly for endangered languages with limited data.
Mod # | Description | ReasonForModification | Federal Obligation | Date |
|---|---|---|---|---|
| Not listed | $300.0k | 8/3/23 |