Language generation, semantically grounded.
Roma, Lazio
Joined July 2016
- Tweets315
- Following48
- Followers407
- Likes685
Babelscape retweeted
Today in @Corriere: my piece on how #public–#private collaboration can accelerate #LLM development, the current #challenges and why stakeholders benefit from making #data available in trusted environments. #AI is not just #technology: It's a #multiplier of #opportunities.
Babelscape retweeted
Had a thoughtful discussion with F. Bongarrà and M. Sebastiani at @iiclondra, covering today's and next-generation trends in #AI and #LLMs, with emphasis on #MinervaLLM, the Italian public pretrained #LLM. Contribute to Minerva: minerva-ai.org italpress.com/allistituto-it…
Babelscape retweeted
Whoa! #ACL2025 was a tremendous success! Thanks to @RNavigli, the conference's general chair, the PCs and all other chairs for this great conference! @aclmeeting #NLP #NLProc
Babelscape retweeted
Even state-of-the-art MT systems struggle with ambiguous words — especially rare senses.
DiBiMT is a new fully human-curated benchmark across 8 language pairs to study disambiguation bias in MT.
📄 Read the paper in Computational Linguistics: direct.mit.edu/coli/article/…
Babelscape retweeted
🚨 It’s happening! The Welcome Address is LIVE at #ACL2025NLP 🇦🇹
🎙️ Local welcome + key program stats
📈 Selection insights from the chairs
🎯 Preview of what’s ahead
Follow along as we officially kick off the conference!
#NLProc #ACL2025NLP
Babelscape retweeted
Hope you all enjoyed the vibrant poster session on Day 1 of ACL 2025! 🎉What were your highlights? 👇 #ACL2025NLP #Postersession #NLProc
Babelscape retweeted
Our Director @RNavigli will chair #ACL2025 @aclmeeting in Vienna, July 27-August 1, 2025. @SapienzaRoma @babelscape @Agenzia_Ansa
ansa.it/osservatorio_intelli…
Babelscape retweeted
✨Did you know that 𝐌𝐓 𝐦𝐨𝐝𝐞𝐥𝐬 𝐚𝐧𝐝 𝐋𝐋𝐌𝐬 still 𝐬𝐭𝐫𝐮𝐠𝐠𝐥𝐞 𝐭𝐨 𝐡𝐚𝐧𝐝𝐥𝐞 𝐥𝐞𝐱𝐢𝐜𝐚𝐥 𝐚𝐦𝐛𝐢𝐠𝐮𝐢𝐭𝐲? direct.mit.edu/coli/article/… #MT #LLMs #NLProc
Babelscape retweeted
Just shared a few thoughts in a recent interview—some tips in there for young/aspiring researchers! Follow your passion! #NLP #research #techtransfer #semantics #LLMs
aihub.org/2025/03/21/intervi…
Babelscape retweeted
Dotato di intelligenza artificiale e tecnologia innovativa, ADRIANO sarà operativo dal 24 marzo 2025, accogliendo cittadini e turisti e fornendo informazioni, in italiano e inglese, sulla storia di Roma e sul sito storico della Camera di Commercio di Roma.
Babelscape retweeted
🚀 Da oggi abbiamo un nuovo collega! Dotato di #IntelligenzaArtificiale e tecnologia innovativa, ADRIANO, un robot sperimentale nato da un'idea della @camcomroma che organizza #MakerFaireRome dal 2013, sarà operativo a partire dal 24 marzo 2025: vienici a trovare (e vienilo a conoscere!) nel Tempio di Vibia Sabina e Adriano, in Piazza di Pietra, a #Roma.
Ti aspettiamo!
📷 In foto: il Presidente della Camera di Commercio di Roma Lorenzo Tagliavanti e ADRIANO.
Babelscape retweeted
🚀Along with our presentation #CLiCit2024, we've just released the Minerva 7B Base and Instruct models on Hugging Face!
🤗huggingface.co/sapienzanlp/M…
🤗huggingface.co/sapienzanlp/M…
All info here: 🖥 nlp.uniroma1.it/minerva
Try the instruct model👉 minerva-llm.org @CLiC_it_conf
Babelscape retweeted
Excited to give an invited talk today on What is Missing in Today's LLMs at the #DiscoveryScience2024 #DS2024 #Conference held in #Pisa ds2024.isti.cnr.it/ #factualityevaluation #safety #grounding #languagecoverage #Minerva #LLMs #AI #NLP #NLProc
Babelscape retweeted
Post #ACL2024nlp dinner in #Bangkok with most of the presenting/attending band from our group + @Babelscape. Left to right: @SBejgu @LorenzoProiet13 @giumartinelli_ @19Stefano97 @RiccardoRicOrl @FMTucci @RNavigli @KarimAsh14 & Celebrating our outstanding paper award! #NLProc
Babelscape retweeted
And yeaaaaaahhhhhhh!!! We did again! Outstanding paper award at #ACL2024 with #NounAtlas, enabling Semantic Role Labeling for nouns! Congrats @marco_lo_pinto, @PasSilvestri, @DennisRotondi, Simone Ciciliano and @alescire94!!! Joint work between @SapienzaNLP & @babelscape! #NLProc
Babelscape retweeted
The #Minerva Italian-English pre-trained #LLM project summarized in English. #generativeAI #NLProc @SapienzaNLP
rivista.ai/2024/05/09/minerv…
Babelscape retweeted
🚀 Introducing the #Minerva Models! The first family of #LLMs trained from scratch on #Italian (& #English). @fondazione_fair @Cineca1969
👉nlp.uniroma1.it/minerva 350M, 1B, 3B base models
🔔Stay tuned for more updates!
#NLProc #MachineLearning #AI #GenerativeNLP #GenerativeAI
Babelscape retweeted
This is the biggest ongoing effort in Italy on #pretrained #LLMs on #Italian and #English with full control of input text. So proud of my @SapienzaNLP group! More soon!
🚀 Introducing the #Minerva Models! The first family of #LLMs trained from scratch on #Italian (& #English). @fondazione_fair @Cineca1969
👉nlp.uniroma1.it/minerva 350M, 1B, 3B base models
🔔Stay tuned for more updates!
#NLProc #MachineLearning #AI #GenerativeNLP #GenerativeAI
Babelscape retweeted
Just interviewed by @alessiojacona @Agenzia_Ansa to talk about #LLMs and the @SapienzaNLP effort to create the first #Italian pre-trained #LLMs, the #Minerva family. Team: @edoardo_barba, @ConiaSimone, @perelluisHC, @AndrewWyn1, @RiccardoRicOrl & me youtube.com/watch?si=O9dafL9…
Babelscape retweeted
Nasce oggi #Minerva, #LLM addestrato da zero per la lingua italiana da @RNavigli e @SapienzaNLP all'interno di #FAIR.
➡️ fondazione-fair.it/news/ai-m…
#intelligenzaartificiale #NLP #GenerativeAI
