CLUE: A Contrastive Learning Framework for Unsupervised Event Type Induction and Annotation

Key points

• Event ontology is the foundational framework for defining events in a dataset.1
• Event type induction generally involves domain experts who define guidelines for creating event types and their names based on the dataset's domain and scope.1
• However, this process is resource-intensive in terms of annotation costs and is prone to human biases.1
• Our main contributions in this work are: 1) designing a novel joint embedding representation for expressing both the verb-centric view and the semantic view of events; 2) event type induction using contrastive loss guided clustering; 3) event naming and refinement.1

Sources (1)

• [1]CLUE: A Contrastive Learning Framework for Unsupervised Event Type Induction and Annotation
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 06:05 PM

  To alleviate the need for manual event ontology creation, we propose the CLUE framework for event type induction, naming, and annotation.

  Event ontology is the foundational framework for defining events in a dataset.

Extractive summary: sentences quoted from the sources.