What is the "DNA of language"? Find out more here (with a short summary of the MOUSSE @ERC_Research project): https://t.co/q5VZ23TDjs
More #AI breakthroughs: https://t.co/HHuWL7QIOV #NLProc@CORDIS_EU#languages#semantics
Very cool (outstanding) reality check paper by former advisor @RNavigli and colleague @SimoneTedeschi_ (+a lot of brilliant minds from all over the world)! A call out to everyone to collaborate for fairer and more transparent evaluation in #NLProc! #acl2023@SapienzaNLP
Thrilled to announce that we received the *outstanding paper award* at ACL 2023 for our paper "What's the meaning of superhuman performance in today's NLU"! https://t.co/Poox6S0H6E
#NLProc#ACL2023#ACL2023NLP
I am especially happy about this paper as it was my first time supervising a student. Congrats to @pavlo_vasylenko for his amazing work, very proud of you!
💡 Through self-knowledge distillation and word-to-node alignment, we achieve state-of-the-art AMR parsing results. Our experiments demonstrate the effectiveness of our approach. #StateOfTheArt#NLPResearch 🧵4/5
I am very happy to present the multilingual expansion of REBEL at #ACL2023. This work has been a year-long effort to try and provide datasets and models that enable high-quality multilingual Relation Extraction on par with English.
🏆When evaluated on BookSum, our LED-based approach achieves state-of-the-art performance (ROUGE-1: 42.13, ROUGE-2: 10.53, and ROUGE-L: 16.75).
Our achievement is attained using only 0.1% of the parameters utilized by the GPT-3-based competitor (Wu et al., 2021).
🧵5/6