Reasoned Translation: Putting Neural Machine Translation and Generative Artificial Intelligence Systems to the “Delisle Test”
Bibliographic record
Abstract
This paper reports on a 2-stage experiment aimed at assessing machines’ ability to “reason” in translation The experiment was built around Jean Delisle’s pedagogy textbook La traduction raisonnée which has been used in English-French translator training for more than 40 years, in Canada and around the world. We put Bing Translator, Google Translate and DeepL – neural machine translation systems – as well as ChatGPT, NotionAI and Gaby-T – generative AI systems – to the test, using a selection of examples taken from the textbook and analyzing the results considering the background information and explanations provided, more specifically in the 30 chapters from where the examples were taken. In this paper, we first explore what inspired Delisle’s work and what he means by “reasoned translation”. Then, we focus on presenting the methodology and the results of our two pilot main experiments. Lastly, we offer some insights into potential future research avenues in translator training and beyond.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".