I'm presenting our new ✨Univeral NER dataset✨ at 2 PM tomorrow at #NAACL2024 (in Don Diego, Poster Session 2). Stop by if you're interested in multilingual benchmarks and/or cross-lingual NER!

We will present two papers at #NAACL2024 this week. I'm looking forward to meeting people interested in multimodality! CompAct by Semih Yagcioglu+ on Wed at 09:36 in Don Alberto 2 aclanthology.org/2024.naacl-lon… PAELLA by Rita Ramos+ on Wed at 11:00 in Poster 7 aclanthology.org/2024.findings-…

My first in-person conference at #NAACL2024 🇲🇽 @_Yucheng_Jiang and I will present STORM🌪️ 𝘁𝗼𝗱𝗮𝘆 𝗮𝘁 𝟮𝗣𝗠 (📍Don Diego 2,3,4).  Would love to chat about report generation, lessons learned in hosting the web demo, and share a bit of what we are cooking after STORM!

Kreyòl-MT arxiv:arxiv.org/abs/2405.05376 github: github.com/JHU-CLSP/Kreyo… x.com/m2saxon/status…

From poster session 2: "Benchmark Transparency" Samplewise proxy model features (ie difficulty, discriminatory power, etc) over examples in a benchmark can predict task transfer via their comparison in domain. From Venelin Kovatchev Anthology: aclanthology.org/2024.naacl-lon…

Venelin Kovatchev "Deceptive Semantic Shortcuts on Reasoning Chains" LLM multihop reasoning difficulty does NOT depend on depth of reasoning chain; rather on similarity between conditioning entity and answer entity From Banzheng Li Ben Zhou 🌴Muhao Chen🌴 Anthology: aclanthology.org/2024.naacl-lon…

How do you do language ID on low-resource or dialectal speech data with very few labels? Check out “Where are you from?” poster #61 going on now at #NAACL2024 or just try our live demo and have our model predict where you are from. huggingface.co/spaces/geoloca…

So excited about this panel! I believe education is one of the most profoundly affected domains by generative AI. It's crucial to explore and address the various aspects and implications #EduTech #GenerativeAI #FutureOfLearning NAACL

Organizing a conference entails months of work from a lot of volunteers from our community. Huge thanks to NAACL HLT 2024 GC and PCs for their hard work in putting together a great program! Thanks to the rest of the organizing committee!

#NAACL2024 social event in #MexicoCity

Sequential compositional generalization multimodal models (NAACL oral) From Semih Yagcioglu et al

Yesterday at the #NAACL2024 social event #MexicoCity

#NAACL2024 NAACL HLT 2024 Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks Zhaofeng Wu (Zhaofeng Wu @ ACL) arxiv.org/pdf/2307.02477

Some of the award winners in this edition of #NAACL2024

Best paper awards #NAACL2024 #MexicoCity

First call for papers is out! #NAACL2025 🔴2025.naacl.org/calls/papers/