🧠 We explore how monolingual, bilingual, and code-augmented data shape multilingual continual pretraining across high- to low-resource languages.

Big thanks to my supervisor @tiedeman.bsky.social man.bsky.social, who will be presenting our poster — come say hi!

It’s happening, the 18th MT Marathon (blogs.helsinki.fi/language-tec...) will start tomorrow with a great line-up in our program. Looking forward to see you all in Helsinki!

Hello from Helsinki

📢 First release: 38 monolingual reference LLMs (2.15B params) via #HPLT + #OpenEuroLLM

⚙️Trained on 100B tokens from HPLT v2 dataset
🌍 Cover EU langs + others
⚙️ Based on LLaMA, trained on #LUMI
📈 Useful for evaluation

Downloads + more info at openeurollm.eu/blog/hplt-oe...

Wanna read great demo papers at EMNLP 2025? You can, because remember: It's *YOUR* community too! So roll up your sleeves and join our program committee as a reviewer: docs.google.com/forms/d/e/1F...

📢 [**mala-opus-dedup-2410**](huggingface.co/datasets/MaL...) 🎉

Part of the [**MaLA Corpus**](huggingface.co/collections/...), deduplicated dataset from [OPUS](opus.nlpl.eu) (cutoff Oct 2024) features **16,829 language pairs** with deduplication, normalization, and noise filtering

Join us on May 16 at 10:00 EEST (Helsinki time) for a session hosted by GreenNLP and the NVIDIA AI Technology Center (NVAITC) Finland on developments in NLP technologies using the NeMo framework. greennlp.github.io/news/2025/04...

Call for participation: We just opened the registration for this year's MT Marathon in August in Helsinki, Finland: blogs.helsinki.fi/language-tec..., featuring:

- Ayodele Awokoya
- Wilker Aziz
- Marta Costa-Jussa
- Barry Haddow
- Amit Moryosse
- Sara Papi
- Jörg Tiedemann
- Marco Turchi

The NoDaLiDa x Baltic-HLT Proceedings are up!

See here: www.nodalida-bhlt2025.eu/proceedings

See you also soon in Tallinn!

#NLP #NLProc #nodalida #baltichlt

Separating me from the @helsinki-nlp.bsky.social account is probably a good idea, is it?

There is an open position for a postdoc in our lab in this call. The focus will be on scalable modular NLP with funding from the ERC PoC project MARMoT

I have big news: @ellis.eu has launched its 2nd major research center, @ellisfinland.bsky.social! I have agreed to start as founding director & the first call for PI positions is open. This is a major opportunity for outstanding researchers, join us! ellisinstitute.fi/PI-recruit

ELLIS Institute Finland is hiring Principal Investigators in AI + machine learning. World-class resources for research incl. LUMI supercomputer, generous starting package & professorship affiliation with a university in the world’s happiest country! Apply by March 9: ellisinstitute.fi/PI-recruit

It's time for transparent AI in Europe. It's time for open LLMs as a robust foundation for developing future private and public AI services. It's time for:

OPEN = open-source
Euro = under EU regulations, representing EU values
LLM = LLMs

openeurollm.eu

Time for the first post on Bluesky: the ERC decided to give funding to our proof-of-concept project MARMoT blogs.helsinki.fi/language-tec...