Conference: Special Session on Language Technology at the 2024 Algonquian Conference

This award supports a special session on language technology in conjunction with the 56th Algonquian Conference. The session features speakers on using information technology to advance the study of endangered languages, providing insight into how technology, especially concerning archives, is making the analysis of language faster and more complete, especially for under-resourced languages.

The session is important to fostering scientific collaboration between academic linguists and tribes that are in need of understanding the inner workings of their heritage languages. The ability to make better use of archives enhances the ability of Indigenous and non-Indigenous scholars alike to gain more insights about Native American languages and to advance language revitalization.

There were more than 300 languages spoken in North America at the time of European contact. There are perhaps 50 language families that can be recognized for those languages, including the Algonquian family. All the families have different traits, but one consistent feature is the use of complex morphology and a greater importance of verbs than nouns compared to many other languages.

These typological characteristics are very different from English and other languages that have been the subject of most work on language technology. Many recent advances in speech technology are therefore ill-equipped to address Native American languages. In addition, the amount of language material available in Native American languages is usually too restricted for the most common language tools.

This session addresses these problems by presenting tools and techniques that scientists and community members can use to get access to archival material and to optimize how it is used. Although the Algonquian Conference is naturally centered on languages from that family, the tools and techniques presented at this special session are general to any language.

This award is made as part of a funding partnership between the National Science Foundation and the National Endowment for the Humanities for the NSF Dynamic Language Infrastructure – NEH Documenting Endangered Languages Program.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.