Dirk Hovy

🏆 Congrats to @zeerak.bsky.social and @dirkhovy.bsky.social on the 2016 Test of Time Award! 🎉 "Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter" has shaped research on #hatespeech! Paper: aclanthology.org/N16-2013/ #NLProc

Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter - ACL Anthology aclanthology.org View on Bluesky →

#TBT #NLProc 'Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview' by Shah, Schwartz, Dirk Hovy (2020). Dive into their mathematical NLP bias framework, its origins, impacts, and types. #AIEthics aclanthology.org/2020.acl-mai...

aclanthology.org View on Bluesky →

#TBT #NLProc Check out 'Helpful or Hierarchical?' by Rashid, F. et al advocating better non-binary representation in tech. #Inclusion

Helpful or Hierarchical? Predicting the Communicative Strategies of Chat Participants, and their Impact on Success aclanthology.org View on Bluesky →

aclanthology.org/2021.finding...

“We will Reduce Taxes” - Identifying Election Pledges with Language Models aclanthology.org View on Bluesky →

#TBT #NLProc Bianchi, Terragni & Dirk Hovy present a smarter technique for topic modeling. Their method uses contextual embeddings for clear, meaningful word clusters, transforming how we interpret large text collections.

Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence aclanthology.org View on Bluesky →