Chahta Anumpa: A multimodal corpus of the Choctaw Language

Chahta Anumpa: A Multimodal Corpus of the Choctaw Language Jacqueline Brixey, Eli Pincus, Ron Artstein USC Institute for Creative Technologies 12015 E Waterfront Dr, Los Angeles, CA 90094 {brixey, pincus, artstein}@ict.usc.edu Abstract This paper presents a general use corpus for the Native American indigenous language Choctaw. The corpus contains audio, video, and text resources, with many texts also translated in English. The Oklahoma Choctaw and the Mississippi Choctaw variants of the language are represented in the corpus. The data set provides documentation support for the threatened language, and allows researchers and language teachers access to a diverse collection of resources. Keywords: endangered languages, indigenous language, multimodal, Choctaw, Native American languages 1. Introduction This paper introduces a general use corpus for Choctaw, an American indigenous language. The Choctaw language is spoken by the Choctaw tribe, who originally inhabited the southeastern United States. The tribe is the fourth largest indigenous group by population in the United States with 220,000 enrolled members.1 The Choctaw language, how- ever, is classified as “Threatened” by Ethnologue,2 as there are only 10,400 fluent speakers and the language is losing users. While sporadic written records of the language appear as early as 1715 (Sturtevant, 2005, page 16), systematic writ- ing of Choctaw only began with the arrival of American missionaries, led by Rev. Cyrus Byington in 1819 (in- troduction to Byington, 1870). The first text published in Choctaw was the Bible, and this is still the longest published text in the language today. Efforts during the 1900s aimed to forcefully assimilate Native Americans and suppress indigenous languages (Battiste and Henderson, 2000). For this reason, many Native Americans did not learn their ancestral language, and few works are publicly published in these languages. As a result of this history, the Choctaw language has few published works and little text representation online. While work has been undertaken to document the language and conduct linguistic studies, no digital corpus of the Choctaw language exists. The present work has gathered sparse text resources representing different variants of the language from teaching materials, books, and scholarly ma- terial. Video and transcribed audio clips where the Choctaw language is spoken in complete phrases are also included in this corpus. The majority of data in this work has an ac- companying English translation, with a smaller portion in monolingual Choctaw. For most of the world’s languages, no data in a machine- readable format are available for human language technol- ogy applications. Compared to well-resourced languages such as English and French, natural language processing tools for Native American indigenous languages are still 1https://web.archive.org/web/20120512040555/ http://www.ok.gov/oiac/documents/2011.FINAL.WEB.pdf 2https://www.ethnologue.com/language/cho not abundant. The goal of this database is thus to first pre- serve a threatened language. The second contribution is to compile a comprehensive data set of existing resources for novel research opportunities in history, linguistics, and nat- ural language processing. The final contribution is to pro- vide documentation of the language for language learners and teachers, in order to assist in revitalization efforts. 2. Choctaw tribe and language 2.1. People …

Content truncated to 500 words