• The HTREC workshop will be held in Venice on November 7 and 8, 2022 (website).
• Our article on restoring and attributing ancient texts is on the cover of Nature. Find the article here and a post about it from DeepMind here.
• Released language modelling code (CBMS’20).
• Data and code for Toxic spans detection is released (SemEval 2021, Task 5).
• Released the code of toxic language detection in context (ACL’20).
• Our bioCaption PyPi for diagnostic captioning is open (NAACL-HLT 2019, CLEF 2019-2020).