Can language technology help journalists to better understand how what their words are perceived? Can it help to reframe the same content? We're on it Lorentz Center this week! lorentzcenter.nl/watch-your-lan… Faculty of Arts - University of Groningen (co-organised w Chiara Zanchi Leonardo De Cosmo Cycling Professor 🚲 )

📢 New paper! A comprehensive survey on figurative language generation, just out on Association for Computing Machinery Surveys. The paper is open access and all materials are available. Congratulations Huiyuan Lai! GroNLP Faculty of Arts - University of Groningen University of Groningen

🐑 PECoRe repository is now public (github.com/gsarti/pecore) and all model/datasets are available on Hugging Face (huggingface.co/collections/gs…)!

🐑Interested in using PECoRe on your models? Have a look at the Inseq implementation (`inseq attribute-context`)!

Discutendo di stereotipi ci tenevo molto a sfatare quello degli italiani che gesticolano quando parlano.
#NLProc AILC_NLP Università di Pavia Fondazione Ghislieri Linguistics in Pavia

Happy to announce that PECoRe, our framework to verify the trustworthiness of LM generations from model internals, was accepted to #ICLR2024 ! 🎉 Details here ⬇️

Snowy Groningen provides the perfect backdrop for today's contest @GroNLP: Pandoro or Panettone? About twenty of us subjected themselves to substantial tasting (tough life, here).
And the winner is...
(well, poll - and eating - still ongoing 😬)

ACL announcement:
'The ACL Executive Committee has voted to significantly change ACL's approach to protecting anonymous peer review. The change is effective immediately. (1/4) #NLPRoc

Want to work with people doing state-of-the-art NLP research in an amazingly friendly atmosphere in a beautiful town? Join @GroNLP! We have two open assistant prof positions in Language Technology and Humane AI, deadline Feb 1st. rug.nl/about-ug/work-…

Join us at the BlackboxNLP poster session today at 11:00 (in-person at #EMNLP2023 ) for our PECoRe presentation and to grab some Inseq stickers! 🐛 #nlproc

Happy to have had the opportunity to present the work done for my master’s thesis in collaboration with GroNLP at the BlackboxNLP workshop at #EMNLP2023 .

Special thanks to Gabriele Sarti, Malvina Nissim and Elisabetta Fersini who made this possible!

More at arxiv.org/abs/2309.00751

#NLProc

The @GroNLP team is traveling to Singapore to present 8 #EMNLP2023 Main/Findings/Workshops papers! 🐮

Meet Jirui Qi Wietse de Vries (contact me by email) Gabriele Sarti Arianna Bisazza Khalid Al-Khatib Daniel Scalena in person and Lisa Bylinina Tommaso Caselli @[email protected] at the virtual EMNLP 2024!

Our papers ⬇️ #EMNLP23 #nlproc

#CLiCit2023 group picture! CLiC-it Conference #NLProc

🤔Have you ever wondered why generative #AI 's such as #ChatGPT can address certain tasks quite well and completely fail at others? What can they do well, and which things are better done by humans, and why? 🫂
Join us in this interactive event! 📢
👉rug.nl/jantina-tammes…

Last few days to apply for this PhD position. Great project on creativity and (M)Translation led by great colleague Ana Guerberof

I am so proud of what @[email protected]/.bsky.social has achieved so far in his PhD. This interview is amazing, so clear and so easy to follow (if you know Dutch 😇)

Ik voel me heel vereerd dat ik uitgenodigd werd om op de podcast van @womeninc
over mijn PhD-project te praten, en jullie doen echt super werk rondom #MaandVanDeBeeldvorming ! Het was een mooi gesprek vond ik, dus luistertip, al zeg ik het zelf :)

📢 *Looking for a PhD student!*
Hedderik van Rijn and I are starting a super exciting project on using LLMs and adaptive methods to improve learning of complex knowledge, and address implicit biases. Want to do a PhD with us? Get in touch (asap)! GroNLP University of Groningen Jantina Tammes School: Digital Society, Tech & AI

[1/8] Our new work (w/ Arianna Bisazza Grzegorz Chrupała 🇪🇺🇺🇦 Malvina Nissim) is finally out! 🎉

We introduce PECoRe, an interpretability framework using model internals to identify & attribute context dependence in language models.

📄Paper: arxiv.org/abs/2310.01188

#NLProc #neuralempty

New paper (in IT) published on Sistemi Intelligenti with Tommaso Caselli @[email protected] Malvina Nissim Viviana Patti

'Sono solo parole. ChatGPT: anatomia e raccomandazioni per l'uso' rivisteweb.it/doi/10.1422/10…

#llm #llm s #chatgpt #AI #NLP

Thanks Valentina Bambini & Chiara Barattieri di San Pietro for this great issue!

The ACL Survey on the Anonymity Period Policy is out:
aclweb.org/portal/content…