PhD @UniMelb | Tech Lead @CatalpaDev Based in 🇮🇩, worked in🇹🇱 🇵🇬 AI, languages, governance, in no particular (world) order
Melbourne, Australia
Joined January 2012
- Tweets622
- Following851
- Followers534
- Likes4.3K
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!
Raphaël Merx retweeted
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! 👇
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 🇻🇺
✨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
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!
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.
Raphaël Merx retweeted
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
Life update: after 10 years in industry, I'm going back to school for a PhD at Uni. of Melbourne!
Started last week, lots of work to do which i'm really looking forward to !
✨A very warm welcome to @RaphaelMerx who is joining #UniMelb #NLProc group to work on enhancing Machine Translation for Medical Education in Timor-Leste! Recently Rapha has presented his first paper on MT for the Mambai Language: aclanthology.org/2024.eurali… !
Coming to Google Translate: Tetun, Tok Pisin, Balinese, Fijian, Acehnese, and many other languages of SEA & the Pacific!
Let's test quality when they release, but potentially a small revolution in MT for our region
blog.google/products/transla…
First paper published!
We create a first corpus for the Mambai language (from Timor-Leste), and try teach an LLM to translate into Mambai using examples selected to match the source, all from one language manual.
arxiv.org/abs/2404.04809
Anyways, goes to show the importance of working with native speakers for low resource NLP work, especially in the LLM era, when benchmarks are less trustworthy than ever!
Also, the #EURALI folks are very cool and i'm looking forward to more work with them! xitter.cf/sina_ahm/status/179439…
#nlproc #lreccoling2024
Thanks all for attending #EURALI today! Let’s hope that such research communities along with language enthusiasts and linguists change the landscape of #nlproc for under-resourced languages in the near future! 🙂
#lreccoling2024
High internet use but low social media use, hats off to 🇩🇪!
Survey by @pewresearch pewresearch.org/short-reads/…
Raphaël Merx retweeted
This #InternationalWomensDay we pay tribute to the wonder women of Catalpa, who are not just smart and skilled but also fearless, funny and feisty!
We spoke to 7 women about their jobs, their career paths and their wishes for women and girls on this day.
catalpa.io/blog/celebrating-…
Woke up watching this series of short videos on Papuan languages, very nice: youtube.com/watch?v=1l5jJE-1…
Lots of trivia, like the Bukiyip system having two counting systems, one in base 3 (for coconuts and fish), one in base 4 (for betel nuts and bananas)