Digital linguists work to save the Arapaho language
Arapaho is one of many indigenous languages ​​at serious risk of extinction. According to the United Nations, 4 out of 10 indigenous languages ​​are currently at risk due to an aging population and continued discrimination against native speakers. For Arapaho, the population of native speakers of the language rooted in the Great Plains is aging. In an effort to prevent its disappearance, a team from the University of Colorado (CU) Boulder and the Northern Arapaho Language and Culture Commission are deploying digital tools, including databases and language teaching projects.
“Arapaho was the native language of Boulder, so when I got hired at CU, I decided, well, I’m going to look into Arapaho,” Andrew Cowell, a linguistics professor at the University of Colorado Boulder and director of the Center for American Indian and Indigenous Studies, said in a statement. “I started getting more and more interested in Arapaho and doing more side work, and eventually decided to change departments to linguistics so I could focus all my energy on indigenous languages. »
Cowell worked on a free online lexical database, containing over 20,000 entries, similar to a dictionary, and on a text database containing over 100,000 Arapaho phrases. These phrases include several natural conversations and stories the team has recorded over the years. Cowell transcribed and translated the recordings, and the sentences are accompanied by linguistic analysis. In total, their data represents almost 100 native speakers.
Although the text database is novel, it has already supported important projects aimed at preserving Arapaho and making learning the language more accessible.
[ Related: A lost ancient language may be hiding in plain sight. ]
“We got a list of the frequency of all the nouns in the language and all the verbs,” Cowell explained. “We categorized them, and that allowed us to produce a very small student dictionary in which we only included words that appear about 40 times or more. That means (students) don’t have to flip through rare and uncommon words that probably won’t interest them as initial learners.”
Cowell and his colleagues are also working on a program to teach Arapaho. As the language is traditionally learned at home and not in an academic setting, the team had to develop the educational structure from scratch.
“It’s all based on looking at the text we’ve collected and seeing how common certain types of grammatical features appear,” Cowell explained. “With Arapaho, no one has ever really tried to teach it as a second language. Now we’re trying to learn it and teach it, and the databases have allowed us to actually produce this program at scale.”
These efforts align with his goal of producing work that will benefit the Indigenous community. In Cowell’s experience, indigenous communities view language as an essential part of their identity. One of the reasons why the full-text database is not publicly available is the fear that it will be used or exploited by artificial intelligence. However, 5,000 sentences approved by native Arapaho speakers will be published online.
House of the Future Prize 2025
