Bridge pre-training and clustering: a unified contrastive learning framework for ood intent discovery

HIGHLIGHTS

• who: Bridge Pre-training and collaborators from the School of Artificial intelligence, University of Posts and Telecommunications, China have published the article: Bridge Pre-training and Clustering: A Unified Contrastive Learning Framework for OOD Intent Discovery, in the Journal: (JOURNAL)
• what: The authors propose an efficient contrastive learning framework to discover OOD intents bridging the gap between IND stage and OOD stage. Besides the authors propose an adaptive contrastive learning (ACL) method to automatically adjust the weights of different negative sample pairs for given anchor according to their semantic similarities. Combining the pre-training stage . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.