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

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 collaboration 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 family), release of what is probably the largest available corpus of sentences in a polysynthetic language (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 prediction and read-along audiobooks for Indigenous languages, and several other subprojects. Sociolinguistic BackgroundThere are about 70 Indigenous languages from 10 distinct language families currently spoken in Canada (Rice, 2008). Most of these languages have complex morphology; they are polysynthetic or agglutinative. Commonly, a single word carries the meaning of an entire clause in Indo-European languages.

Phoneme transcription of endangered languages: an evaluation of recent ASR architectures in the single speaker scenario

“…We also had access to transcribed Inuktitut, Cree and Tsuut'inai recordings collected and transcribed during the NRC Indigenous language project (Kuhn et al, 2020). We selected a single speaker subset from each language.…”

Indigenous language technologies: Anti-colonial oases in a colonizing (digital) world

“…Galla (2018) conveys the complexity of this relationship as the proverbial "two-edged sword," recognizing the harm inflicted on Indigenous communities by hegemonic languages, but also feeling the necessity of active engagement with technology to ensure language survival. Many Indigenous language communities are looking at ILTs as potential tools for Indigenous language revitalization (ILR) (Galla, 2009;Keegan & Cunliffe, 2014;Kuhn et al, 2020;Littell et al, 2018;Wagner, 2017), and it is exciting to think of talking to "Siri" in a small Indigenous language. However, with the negative financial pressure facing the development of ILTs by the world's large technology companies, Indigenous people must take the lead in developing the next wave of responsive and responsible language technologies.…”

“…To meet the challenges outlined above, many communities in Canada are collaborating with non-profit partners for the development of ILT outside of a profit-driven ecosystem (Kuhn et al, 2020;Littell et al, 2018;Rice & Thieberger, 2018). These innovative partnerships include universities, communities, research institutions, governments, and others, which go beyond simply decolonizing these spaces into active anti-colonial work that challenges systemic and technological limits to advance the presence of Indigenous languages in the digital world.…”

“…As such, a research partnership between the language community and a university (in this case through a PhD student) is an ideal vehicle to complete this work. This type of innovative research is stimulating and challenging and there are many non-Indigenous researchers/allies who are intensely interested in helping communities solve technical challenges (Kuhn et al, 2020).…”

“…As language technology tools are developed, it is in the collective interest to see that they are shared and adaptable for other languages. This open source approach guides the work of the National Research Council of Canada Indigenous Languages Technology unit in an empowerment based approach (Kuhn et al, 2020). As tools are created in partnership with Indigenous communities, they are released for other communities and languages to adapt to local needs.…”