@RaphaelMerx

PhD @UniMelb | Tech Lead @CatalpaDev Based in 🇮🇩, worked in🇹🇱 🇵🇬 AI, languages, governance, in no particular (world) order

 Melbourne, Australia
rapha.dev
Joined January 2012
  • Tweets621
  • Following850
  • Followers532
65Media
Include

Only show posts containing:

Exclude

Hide posts containing:

Time range
-
Minimum likes
Replying to @ivrik
Kat, I'm infinitely sad reading this. May you, Andreas, and your son, find the strength to go through this, and may Lea continue her loving life in a better world.
1
2
66
arxiv.org/abs/2508.16048

OpenWHO: A Document-Level Parallel Corpus for Health Translation...

In machine translation (MT), health is a high-stakes domain characterised by widespread deployment and domain-specific vocabulary. However, there is a lack of MT evaluation datasets for...

arxiv.org
1
1
86
Our #WMT2025 paper got accepted 🙌 We release a dataset for health low-res MT... and find that Gemini 2.5 beats NLLB 54B, if given full document context. Seeya in Suzhou!
2
1
1
4
419
Did you know? ❌77% of language models on @huggingface are not tagged for any language 📈For 95% of languages, most models are multilingual 🚨88% of models with tags are trained on English In a new blog post, @tylerachang and I dig into these trends and why they matter! 👇
2
4
25
1,250
Replying to @davlanade @SenyuLiReal @alabi_jesujoba
Really cool work, the AfriDoc-MT paper in particular is a trove of interesting findings on doc Vs sent level translation in low-res MT
3
89
paper: aclanthology.org/2025.acl-de… demo: youtu.be/fQFwOxzR4MI Grateful for all the help and advice from my supervisors Hanna Suominen, Nick Thieberger, Trevor Cohn, Katerina Vylomova, and special thanks to Maluk Timor & Lois Hong for the great joint work!

Tulun: Transparent and Adaptable Low-resource Machine Translation

Raphael Merx, Hanna Suominen, Lois Yinghui Hong, Nick Thieberger, Trevor Cohn, Ekaterina Vylomova. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3:...

aclanthology.org
3
92
in Vienna for ACL, presenting Tulun, a system for low-resource in-domain translation, using LLMs Working w 2 real use cases: medical translation into Tetun 🇹🇱 & disaster relief speech translation in Bislama 🇻🇺
Kat Vylomova (कत् विलोमोव) 🕊️@ivrik27 Jul 2025
Replying to @ivrik
✨TULUN: Transparent and Adaptable Low-resource Machine Translation By: Raphael Merx, Hanna Suominen, Lois Yinghui Hong, Nick Thieberger, Trevor Cohn, Kat Vylomova Paper: aclanthology.org/2025.acl-de… Demo: bislama-trans.rapha.dev #ACL2025NLP #NLProc #ACL2025
1
2
5
378
Replying to @YasminMoslem @AdaptCentre @tcddublin @Huawei
Congrats Yasmin!
1
19
Replying to @prajdabre
must be stressful... I'm sure you'll find something good though, smart driven people like you always land on their feet!
1
67
Replying to @wbyanme
there's curse in Cursor for a reason
1
1
32
Replying to @prajdabre @geoffreyhinton @JeffDean @OriolVinyalsML
Whoa that's very cool! Didn't think I'd meet Taylor series approximation again in my lifetime
97
Replying to @wbyanme
Legit good, became aware of the Trudeau resignation through this
1
1
36
Replying to @jlibovicky
Enjoyed reading this, thanks for sharing!
17
Our paper on generating bilingual example sentences with LLMs got best paper award @altanlp ! arxiv.org/abs/2410.03182 We work with French / Indonesian / Tetun, find that annotators don't agree about what's a "good example", but that LLMs can align with a specific annotator.
3
4
18
1,042
Replying to @KushalTatariya @akulmizev @EstherPloeger @mmbollmann @johannesbjerva @mdlhx @lagom_nlp
Really nice paper, definitely saving this as inspiration for work on data quality! For §5, you maybe you'd have seen more correlation btw quality & performance on NLG tasks, instead of NLU? As NLG would suffer from low-quality training data, more than NLU, I think?
2
93
Replying to @zouharvi
Cool work, appreciate the video, and fire poster! Can I ask what you used to design it?
1
1
43
Replying to @prajdabre @NeurIPSConf
Enjoy precious moments with family, congrats to all 3 of you!
1
210
Replying to @sethjsa @davidstap @diwuNLP @c_monz @illc_amsterdam @ltl_uva
Super interesting! In a similar vein, we studied MT using LLMs w sentences from a language manual for Mambai, and found that while scores were decent on test sentences sampled from the manual, it collapsed on sentences translated by a native speaker: aclanthology.org/2024.eurali…

Low-Resource Machine Translation through Retrieval-Augmented LLM Prompting: A Study on the Mambai...

Raphaël Merx, Aso Mahmudi, Katrina Langford, Leo Alberto de Araujo, Ekaterina Vylomova. Proceedings of the 2nd Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced...

aclanthology.org
1
5
254
Replying to @prajdabre
So cool Raj! Your mom can now say she's made two significant contributions to the NLP community, research and a researcher
1
1
130
Translation is a complex task involving pre-translation research and post-translation stages. Can #LLMs handle this process step-by-step, relying solely on their internal knowledge? ✨We show that decomposing the translation process significantly improves #Gemini translation quality of long-form texts across all #WMT24 languages! 📜arxiv.org/pdf/2409.06790
2
14
2
69
6,591
Load more