RResearcharAcademic radar for researchers

Feed Venues Groups Network Inbox Profile

Your academic radar

One personalized feed of papers, calls for papers, collaborators and datasets — plus research groups and paid-in-points study recruitment.

Create account Log in

Top venues

Browse all

Loading…

Medical translation errors: No Language Left Behind glossary vs fine-tune 22% vs 46% 2026 · Researchar

Back to feed

Paperopenalex

ZCE

Medical translation errors: No Language Left Behind glossary vs fine-tune 22% vs 46% 2026

Lauren Sanders · Zenodo (CERN European Organization for Nuclear Research) 2026 · 2026

DOI: 10.5281/zenodo.22800290

0citations

Natural Language Processing TechniquesArtificial Intelligence in Healthcare and EducationGenomics and Rare DiseasesMirroringGlossaryLinguistics+2

ZCEZenodo (CERN European Organization for Nuclear Research)Repository

Download PDF Publisher

Medical translation errors: No Language Left Behind glossary vs fine-tune 22% vs 46% 2026

Open Access

Lauren Sanders·Zenodo (CERN European Organization for Nuclear Research)(2026)

Download Open in tab

Viewing in embedded reader. If this publisher restricts inline iframe preview:

Open directly Download PDF

Citations by source

Synced 2026-09-18T02:30:17.089321Z

0OpenAlex · primary0Semantic Scholar0Crossref

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

Abstract

Medical translation errors: comparing NLLB glossary constraints vs fine-tuning lifts term adherence from 36.67% to 72.88%. See which 2026 method wins. Independent technical note mirroring the canonical version: https://aitranslations.io/blog/medical-translation-errors-no-language-left-behind-glossary-vs-fine-tune-22-vs-46-2026.php

Discussion (0)

No comments yet — start the discussion below.