@mjjzha
Postdoc — University of Copenhagen #NLPxEducation #NLPxHR #NLP Past: 🇩🇰 Aalborg University 🇩🇰 IT University of Copenhagen 🇨🇭 EPFL 🇸🇬 National University of Singapore 🇩🇪 NEC 🇳🇱 University of Groningen 🌐 https://jjzha.github.io/
Announcing our latest paper: CommonLID
In collaboration with @commoncrawl.bsky.social @mlcommons.org @jhu.edu we built a LID benchmark on actual Common Crawl text covering 109 languages. Existing evaluations overestimate how well LangID works on web data.
arxiv.org/abs/2601.18026
Are you attending NAACL 2025 and are you interested in low-resource languages and dialects?
Then don't miss our very own @verenablaschke.bsky.social's keynote talk at the WNUT 2025 workshop on May 3rd:
Beyond “noisy” text: How (and why) to process dialect data
🌐 ☀️
noisy-text.github.io/2025/
🚀 We are excited to introduce Kaleidoscope, the largest culturally-authentic exam benchmark.
📌 Most VLM benchmarks are English-centric or rely on translations—missing linguistic & cultural nuance. Kaleidoscope expands in-language multilingual 🌎 & multimodal 👀 VLMs evaluation
NoDaLiDa x Baltic-HLT 2025 is a wrap!
Thank you all for joining for a fruitful conference! Safe trip home and see you in Copenhagen or Vilnius in 2027!!
#nlp #nodalida #baltichlt
NoDaLiDa 2027 will be held at the Center of Language Technology at the University of Copenhagen!!
#nodalida #nlp
Welcome to NoDaLiDa / Baltic-HLT 2025!
After the opening speech (9:00), we're kicking of with the opening keynote by
Prof. @arianna-bis.bsky.social (09:20-10:10): "Not all Language Models need to be Large: Studying Language Evolution and Acquisition with Modern Neural Networks". (in Lääne-Euroopa)
The first day of workshops is almost a wrap! Join us later today at the welcome reception at the Institute of the Estonian Language (maps.app.goo.gl/brzig4jP6ZfZ...) from 18:30 onwards!!
#nlp #nodalida #baltichlt
Now conference-approved!
#nlp #nlproc #nodalida #baltichlt #tallinn
Morning!!! We're excited to welcome you in Tallinn!
On March 2nd (Sunday), we're starting with workshops in the Hestia Hotel Europa:
RESOURCEFUL 2025 (9:00-17:00): shorturl.at/HypPv
NB-REAL 2025 (9:00-13:00): nbreal.xyz
NLP4Ecology 2025 (13:30-17:30): nlp4ecology2025.di.unito.it
#nlp #nlproc
Heading to Tallinn for @nodalida.bsky.social! 🇪🇪 We’re presenting our work on:
🇩🇰 Sun, Mar 2: "DaKultur: Evaluating the Cultural Awareness of LLMs for Danish“ (10:30)
🤖 Tue, Mar 4: "SnakModel: Lessons from Training Our Open Danish LLM" (10:45)
Finally, networking over some lovely Estonian soup! 🍲
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
The Lisbon Machine Learning Summer School (LxMLS) 2025 is now open for applications.
I’ve done the Covid version myself, and I found the content to be very useful. I went to Lisbon on another occasion, which is also a huge recommendation!!
lxmls.it.pt/2025/
The technical report is now out, loads of interesting insights into multilingual LLM pre-training ✍️
arxiv.org/abs/2502.12982
Congrats Longxu, Qian, Fan, Changyu and team!
#nlp
This work has now been accepted at #CVPR2025 🤘
🚀 Thank you all for waiting! The full program of NoDaLiDa x Baltic-HLT is online:
www.nodalida-bhlt2025.eu/program
#nodalida #baltichlt #nlp #nlproc
NoDaLiDa/Baltic-HLT is in less than two weeks!
Some of the places you can visit:
Kalamaja, one of Tallinn's oldest districts, is known for its wooden houses and hipster vibe, with Telliskivi Creative City as its cultural hub. Nearby, Noblessner offers waterfront views and diverse dining options.
Looking for a PhD student to come work with me on the ethical implications of NLP from September!
Please share widely and point any interesting students my way! 😊
The NLP group at Aalborg University (*Copenhagen campus*) is hiring a postdoc in NLP Security:
(ddl: 15 April)
www.vacancies.aau.dk/scientific-p...
#nlproc #nlp #aau
Otherwise there is also the Pierre Chocolaterie in the hidden Masters’ Courtyard, or a number of other trendy establishments. When it comes to views, you can’t beat those from the Old Town Wall, its towers and Toompea Hill’s viewing platforms!!
See you soon!
#nodalida #baltichlt #nlp #nlproc
NoDaLiDa/Baltic-HLT is less than a month away!
Did you know Talllinn is a living UNESCO treasure and also has a café culture? One such example is Maiasmokk, the oldest café in Tallinn dating back to 1864!
Appreciate it! Attached a new post with working links
Now with working links:
Doc: docs.google.com/document/d/1...
Spreadsheet: docs.google.com/spreadsheets...
(DL end of Jan 2025)
We're missing coverage in Europe, especially from high resource languages like French, German, Italian. If you're interested, check our guidelines (docs.google.com/document/d/1...) and suggestions google sheet (docs.google.com/spreadsheets...).
Join us on the Aya Discord: discord.gg/4B5tEdbP
#NLP
Hi folks, in collaboration with @cohereforai.bsky.social, we're looking for contributors to a Multilingual **Multimodal** Exams benchmark in MCQ style. What's in it for you:
Submit 1000Qs for high/mid-resource, or for 500 low-resource langs to be eligible for co-authorship.
9.6 million seconds = 1 PhD 🔥
Finally analyzed my PhD time tracking data so you can plan your own research journey more effectively: mxij.me/x/phd-learning-dynamics
For current students: I hope this helps put your journey into perspective. Wishing you all the best!
The paper is going to be presented @nodalida.bsky.social:
📄: arxiv.org/abs/2412.12956
💻: github.com/nlpnorth/sna...
🤗: huggingface.co/NLPnorth/sna...
Nice to see @mjjzha.bsky.social presenting our joint collaboration with Aallborg University: SnakModel, a new language model for Danish 🇩🇰
(w/ @mxijme.bsky.social @elisabassignana.bsky.social and Rob van der Goot)
Thanks for the warm invite @dnnslmr.bsky.social !!!