Roberto Navigli

601 posts

Roberto Navigli banner
Roberto Navigli

Roberto Navigli

@RNavigli

Prof @SapienzaRoma, head @SapienzaNLP, ACL Fellow, BabelNet creator (https://t.co/p56mB41mIA), co-founder @Babelscape https://t.co/PMmnxc7IsN #NLProc #multilinguality

Rome, Italy Katılım Mayıs 2013
298 Takip Edilen1.7K Takipçiler
Roberto Navigli retweetledi
Computational Linguistics Journal
Computational Linguistics Journal@CompLingJournal·
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/5…
Computational Linguistics Journal tweet media
English
0
4
23
2.1K
Roberto Navigli retweetledi
ACL 2026
ACL 2026@aclmeeting·
🚨 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
ACL 2026 tweet media
English
2
6
55
3.9K
Roberto Navigli retweetledi
ACL 2026
ACL 2026@aclmeeting·
Hope you all enjoyed the vibrant poster session on Day 1 of ACL 2025! 🎉What were your highlights? 👇 #ACL2025NLP #Postersession #NLProc
ACL 2026 tweet mediaACL 2026 tweet media
English
1
6
50
3.9K
Roberto Navigli retweetledi
SapienzaNLP
SapienzaNLP@SapienzaNLP·
We've landed in Vienna for #ACL2025! 🇦🇹 Proud to present 4 accepted papers on MT evaluation, coreference resolution, word sense disambiguation & LLM evaluation. Thread below 👇
SapienzaNLP tweet media
English
1
4
7
293
Roberto Navigli
Roberto Navigli@RNavigli·
🧪 Are our standard evaluation settings really capturing a system’s true disambiguation power?
English
0
0
4
132
Roberto Navigli
Roberto Navigli@RNavigli·
⚙️ How does model capacity affect a system’s ability to represent multiple senses of the same word? 🌐 Do multilingual models trade off fine-grained disambiguation to cover more languages? 📈 What role does beam search play in a model’s ability to choose the correct sense?
Roberto Navigli tweet media
English
1
0
5
174
Roberto Navigli
Roberto Navigli@RNavigli·
✨Did you know that 𝐌𝐓 𝐦𝐨𝐝𝐞𝐥𝐬 𝐚𝐧𝐝 𝐋𝐋𝐌𝐬 still 𝐬𝐭𝐫𝐮𝐠𝐠𝐥𝐞 𝐭𝐨 𝐡𝐚𝐧𝐝𝐥𝐞 𝐥𝐞𝐱𝐢𝐜𝐚𝐥 𝐚𝐦𝐛𝐢𝐠𝐮𝐢𝐭𝐲? direct.mit.edu/coli/article/5… #MT #LLMs #NLProc
English
1
4
7
441
Roberto Navigli retweetledi
ACL 2026
ACL 2026@aclmeeting·
📢Student Volunteer Call is now OPEN! Help make ACL 2025 a success — support the organizing team and gain valuable experience. In return, your conference registration is covered. Deadline 🗓️ June 16. Call 👉2025.aclweb.org/calls/voluntee… #StudentVolunteers #ACL25
English
0
8
27
4K
Roberto Navigli retweetledi
ACL 2026
ACL 2026@aclmeeting·
📢 Attending ACL 2025 and need a visa 🪪? Check the visa page of ACL 2025 to find information about: - who needs a visa - visa categories - invitation letter 📃 - recommendations for embassies Find more information at 2025.aclweb.org/visa/ #ACL2025NLP #nlproc
English
0
5
16
4K
Roberto Navigli retweetledi
ACL 2026
ACL 2026@aclmeeting·
🔔🔔🔔 #ACL2025NLP Birds of a Feather (BoF) and Affinity Group meetings! 🐦🤝 Check 👉2025.aclweb.org/calls/bof_affi… 💡 If interested in organizing a specific theme in NLP 🗣️ or beyond 🗓️May 25, 2025, 11:59pm (AoE) 🙌
English
0
4
12
3.2K
Roberto Navigli retweetledi
ACL 2026
ACL 2026@aclmeeting·
📢The Calls for D&I Subsidies (in-person and virtual) are now open! We invite researchers from marginalized communities and with financial hurdles to apply by June 6, 2025 11:59pm (AoE) 🗺️ Main Call 👉 2025.aclweb.org/calls/subsidie… Virtual Non-Presenters Only 👉2025.aclweb.org/calls/virtual_…
English
1
9
17
4.5K