Lost in Innu-Aimun Translation - Re-dening Neural Machine Translation for Indigenous Interpreters and Translators Needs
Bibliographic record
Abstract
Innu-Aimun, one of the most spoken Indigenous languages in Canada, faces signicant transmission challenges.Although there is a notable body of Innu-Aimun literature, there is generally not enough documentation written in Innu-Aimun for daily use, just as there are not enough translators and interpreters for the language.We present here collaborative work between Innu-Aimun translators and researchers in computational linguistics to develop translation assistance tools, with the aim of helping language revitalization and preservation.We detail our common position on how should technological assistance tools be developed for Innu-Aimun, which emphasizes the importance of involving Innu translators throughout the entire process and making sure to address language-specic needs.This position is elaborated from joining our respective perspectives (researchers and Innu community member) and expertise (computational linguistics and Innu-Aimun translation).In this spirit, we present preliminary results for the rst ongoing steps towards building a rst Innu-Aimun -French Neural Machine Translation model.We focus on our participatory process to create aligned parallel corpora and present rst results and analyses.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.021 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.004 | 0.003 |
| Scholarly communication | 0.007 | 0.006 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.012 | 0.004 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".