Rohit Ghumare ede4a3e889 feat(phase-05/11): machine translation ...

Production 2026 MT pipeline. NLLB-200 / mBART / Marian by use case.
Working BLEU + chrF computation in pure Python (with the exact
sacrebleu caveat about tokenization inconsistency being the most
common silent benchmark bug).

Names the five production failure modes research flags: hallucination,
off-target generation, terminology drift, formality mismatch, length
explosion on short input. Each with a concrete mitigation.

Fine-tuning recipe for domain adaptation. Decision table for picking
between NLLB-200, mBART, Marian, and LLM-based translation.

Ship artifact: mt-evaluator skill with the 5-point shipping checklist
and refusal rules (no ship without language-ID check, no reference-free
scoring without explicit opt-in).

~75 minutes. Prerequisites lesson 05/10 and 05/04.

2026-04-22 17:34:58 +01:00

..

mt-pipeline.svg

feat(phase-05/11): machine translation

2026-04-22 17:34:58 +01:00