The Indigenous Languages Technology project at NRC Canada: An empowerment-oriented approach to developing language software

Proceedings of the 28th International Conference on Computational Linguistics, pages 5866–5878 Barcelona, Spain (Online), December 8-13, 2020 5866 The Indigenous Languages Technology project at NRC Canada: An empowerment-oriented approach to developing language software Roland Kuhn, Fineen Davis, Alain Désilets, Eric Joanis, Anna Kazantseva, Rebecca Knowles, Patrick Littell, Delaney Lothian, Aidan Pine, Caroline Running Wolf, Eddie Santos, Darlene Stewart National Research Council Canada (NRC) Firstname.Secondname@nrc-cnrc.gc.ca (e.g., Roland.Kuhn@nrc-cnrc.gc.ca) Gilles Boulianne, Vishwa Gupta Centre de recherche informatique de Montréal (CRIM) gilles.boulianne@crim.ca, vishwa.gupta@crim.ca Owennatékha Brian Maracle Onkwawenna Kentyohkwa (Our Language Society) owennatekha@gmail.com Akwiratékha’ Martin Kahnawà:ke Kanien’kehá:ka Territory tekhaluvsyou@hotmail.com Christopher Cox, Marie-Odile Junker, Olivia Sammons, Delasie Torkornoo Carleton University FirstnameSecondname@cunet.carleton.ca Nathan Thanyehténhas Brinklow Queen’s University and Tsi Tyonnheht Onkwawen:na Language and Cultural Centre (TTO) nathan.brinklow@queensu.ca Sara Child Sa¯nyak¯ola Foundation sanyakola2018@gmail.com Benoît Farley Pirurvik Centre benoitfarley@videotron.ca David Huggins-Daines Nuance Communications dhdaines@gmail.com Daisy Rosenblum University of British Columbia daisy.rosenblum@ubc.ca Heather Souter Prairies to Woodlands Indigenous Language Revitalization Circle p2wilrc@gmail.com 5867 Abstract This paper describes the first, three-year phase of a project at the National Research Council of Canada that creates software to assist Indigenous communities in preserving their languages and extending their use. The project aimed to work within the empowerment paradigm, where collab- oration with communities and fulfillment of their goals is central. Since many of the technologies we developed were in response to community needs, the project ended up as a collection of diverse subprojects, including the creation of a sophisticated framework for building verb conjugators for highly inflectional polysynthetic languages (such as Kanyen’kéha, in the Iroquoian language fam- ily), release of what is probably the largest available corpus of sentences in a polysynthetic lan- guage (Inuktut) aligned with English sentences and experiments with machine translation (MT) systems trained on this corpus, free online services based on automatic speech recognition (ASR) for easing the transcription bottleneck for speech recordings, software for implementing text pre- diction and read-along audiobooks for Indigenous languages, and several other subprojects. 1 Introduction This paper describes the Indigenous Languages Technology (ILT) project at the National Research Coun- cil of Canada (NRC). Phase I of this project received funding of $6 million over three years in the March 2017 budget of the Government of Canada; phase II is ongoing. The project’s goal is to produce soft- ware that will enhance the efforts of Indigenous communities in Canada to preserve and revitalize their languages. Littell et al. (2018) surveys many different efforts by a variety of organizations that have the same goal. This paper depicts a tiny corner of a big canvas; for space reasons, it does not even cover all aspects of our project. For a detailed technical report on the entire ILT project, see Kuhn et al. (2020). Different communities have very different linguistic needs, so the ILT project was made up of a diverse set of subprojects. Because there is relatively little textual or speech data for Indigenous languages in Canada (with the partial exception of Inuktut), most of the technologies developed within the project described here have been rule-based, …

Content truncated to 500 words