Existing approaches to unsupervised commonsense QA usually leverage external KGs, but require large amounts of training examples. We introduce a binary classification approach that uses much less training data. Work led by Jie He to be presented at #ACL2023 - Jeff Z. Pan 👇👇👇

Excited to share that our paper titled "Instances and Labels: Hierarchy-aware Joint Supervised Contrastive Learning for Hierarchical Multi-Label Text Classification" has been accepted at the finding of #emnlp2023 together w/Simon, Víctor Gutiérrez-Basulto, Jeff Z. Pan!🎉 Stay tuned for more.

Happy to announce that @InfAtEd are recruiting a professor in NLP, computer vision, or ML to lead our brand-new Laboratory for Generative AI. Deadline 16 Feb 2024. aspenpeople.co.uk/microsite/uoe-…

The University of Edinburgh is looking for someone to direct a new generative AI lab. It's a professor role, with lots of resources. More info: aspenpeople.co.uk/uoe-gail/ For earlier-career faculty jobs (and a communications role) see: ed.ac.uk/informatics/ab…

Happy to announce that @InfAtEd is hiring a lecturer/reader (assistant/associate prof) in computational cognitive science. Apply by 12 January 2024. Details are here: elxw.fa.em3.oraclecloud.com/hcmUI/Candidat…

Work for us on multilingual NLP! elxw.fa.em3.oraclecloud.com/hcmUI/Candidat…

Super proud of my amazing collaborators for getting two out of two papers accepted at CoLM! (Conference on Language Modeling) 🤗🤗🤗 -- Check out these works on code-to-code translation using LLVM Intermediate Representations as an interlingua (🤯, arxiv.org/abs/2404.16041) and on evaluating the