🥳 Variation Matters is at #AMTA2026! Translating a term two different ways: an error? Humans do it on purpose. Consistency metrics say yes 😬 Our answer: variation-aware evaluation. 🗣️ Oral talk in Québec 🇨🇦, Mon 31 Sept · w/ @ziqianpeng.bsky.social, @rachelbawden.bsky.social & @yvofr.bsky.social ✨
Improving Term Evaluation in Machine Translation: Variation Matters Nicolas Dahan, Ziqian Peng, François Yvon and Rachel Bawden 📅 Monday 31st August | 14:30-14:55 | oral presentation @nicolasdahan.bsky.social @ziqianpeng.bsky.social @rachelbawden.bsky.social @yvofr.bsky.social
Rachel Bawden (@rachelbawden.bsky.social)
Researcher in NLP in the ALMAnaCH team (Inria Paris)
rachelbawden.bsky.social
🎉 ALMAnaCH will be at AMTA 2026 next week 🎉 👏 Congratulations to all authors and collaborators for their contributions on term-aware document-level evaluation of machine translation. Here’s where you can find us:
🥳 MetaDocEval made it to #EAMT2026! Do the metrics we run on whole documents actually capture document-level quality? 😬 Mostly not. 🗣️ Oral talk @eamt2026.bsky.social in Tilburg 🇳🇱, Thu 18 June (#107). Joint work w/ @rachelbawden.bsky.social & @yvofr.bsky.social ✨
MetaDocEval: A Contrastive Framework for Evaluating Machine Translation Metrics at the Document-Level Nicolas Dahan, Rachel Bawden and François Yvon 📅 18th June | 09:05-09:30 | oral