Daily MT Picks
Archives
Search...
Subscribe
Machine Translation Digest for Oct 01 2026
October 2, 2026
One paper argues that a rule-based system still beats fine-tuned neural models for Polish-Silesian, while another takes the opposite tack and tries to...
Machine Translation Digest for Sep 30 2026
October 1, 2026
Shipping translation systems means deciding where consistency, latency, and cost can be bent before they break under real content: long-form subtitles need...
Machine Translation Digest for Sep 29 2026
September 30, 2026
A Greek papyrus HTR pipeline can still support four papyrological tasks even when character error rate is not near zero; in tests on 63,846 current edited...
Machine Translation Digest for Sep 28 2026
September 29, 2026
How do you score a natural-language-to-logic translation when a single quantifier flip can break every proof downstream? One paper answers with SIV, a...
Machine Translation Digest for Sep 27 2026
September 28, 2026
A simple change in loss weighting can make multimodal MT models pay attention to the image when the source text is ambiguous, rather than quietly ignoring...
Machine Translation Digest for Sep 24 2026
September 25, 2026
COILD pushes MT for Indian languages in a more grounded direction, with over 1.16 million human-translated and human-verified sentence pairs across 20...
Machine Translation Digest for Sep 23 2026
September 25, 2026
If your translation system is going into production, the failure mode to worry about is not just lower quality but losing the controls users rely on:...
Machine Translation Digest for Sep 22 2026
September 24, 2026
A speech-translation study on Qwen2.5-Omni-3B across four languages uses group relative policy optimization to score both transcripts and translations,...
Machine Translation Digest for Sep 21 2026
September 24, 2026
What does it take for evaluator signals to become actual fixes, and for those fixes to stay small enough to be useful in production MT? One paper tackles...
Machine Translation Digest for Sep 20 2026
September 24, 2026
A reference-based GEC scorer can be wrong for the reason that matters most: if the reference set misses a valid edit, M² and ERRANT will still mark it down....
Machine Translation Digest for Sep 13 2026
September 24, 2026
The strongest result here is for document-level MT: Fixed-Range Chunking keeps output lengths consistent while cutting the repetition and drift that plague...
Machine Translation Digest for Sep 17 2026
September 22, 2026
Shipping translation systems means more than getting sentence-level fidelity right: if your MT-powered interpreter stumbles on pragmatics, register, or...
Machine Translation Digest for Sep 16 2026
September 21, 2026
Today’s MT digest spotlights work on quality estimation, corpus selection, low-resource translation resources, and multilingual data curation. A clear thread...
Machine Translation Digest for Sep 15 2026
September 20, 2026
Today’s MT research digest spotlights evaluation, control, and accessibility across both text and multimodal settings, with several papers probing how we...
Machine Translation Digest for Sep 14 2026
September 19, 2026
Today’s MT research digest highlights a mix of translation-focused training and evaluation work, with a notable emphasis on judging outputs by their end...
Machine Translation Digest for Sep 11 2026
September 16, 2026
Today’s MT research digest highlights work on document-level translation, evaluation, and multimodal translation, alongside a few adjacent studies on...
Machine Translation Digest for Sep 10 2026
September 15, 2026
Today’s MT research digest spotlights fresh work on translation quality, robustness, and evaluation, with a strong emphasis on separating clean signal from...
Machine Translation Digest for Sep 09 2026
September 14, 2026
Today’s MT research digest spans terminology-aware translation, speech and video understanding, and practical efficiency gains for large models. A common...
Machine Translation Digest for Sep 07 2026
September 12, 2026
Today’s MT research digest highlights a mix of evaluation, robustness, and representation studies, with several papers probing how model behavior changes...
Machine Translation Digest for Sep 04 2026
September 9, 2026
Today’s MT research digest spotlights fresh work on localisation, evaluation, and linguistic structure across multilingual settings. A common thread is the...
Older archives
