Metraipolis › archive › dc_f3deb15c4cea
FACET at WMT 2026 Automated Translation Quality Evaluation Task — arXiv:2610.00096
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.00096
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T13:53:37.163Z
- SHA-256 of the archived text
bc5f619866efcb220f8a7514239fb12011228503daa256c30773dbe0af4aa318- Stable URL of this page
https://metraipolis.com/documento/dc_f3deb15c4cea
How to cite
FACET at WMT 2026 Automated Translation Quality Evaluation Task — arXiv:2610.00096 — arXiv (en), https://arxiv.org/abs/2610.00096 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f3deb15c4cea (Metraipolis archive dc_f3deb15c4cea, sha256 bc5f619866efcb220f8a7514239fb12011228503daa256c30773dbe0af4aa318)
BibTeX
@misc{dcf3deb15c4cea,
title = {FACET at WMT 2026 Automated Translation Quality Evaluation Task — arXiv:2610.00096},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.00096},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f3deb15c4cea; sha256 bc5f619866efcb220f8a7514239fb12011228503daa256c30773dbe0af4aa318},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00096. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Different error types in machine translation require different evidence. Whether meaning is preserved can be judged only against the source, while whether the target is well-formed, or whether it names one entity consistently, can be judged from the target alone. We present FACET, our reference-free submission to the WMT26 Automated Translation Quality Evaluation Task, which decomposes evaluation into Fluency, Accuracy, and Consistency passes and gives each pass only the context its error type requires. A single fixed model is prompted three times, and the merged error spans yield the three task outputs, error spans, quality scores, and error-free labels, with no trained components. We also submit FACET-C, which omits the Consistency pass. Without gold labels, we characterize the predictions of FACET. Its system rankings place post-edited human translation first, and the Consistency pass changes about a tenth of segment scores while leaving the ranking nearly unchanged. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.00096 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T12:15:34.600Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).