Improving Event Definition Following For Zero-Shot Event Detection

arXiv:2403.02586v1 Announce Type: new
Abstract: Existing approaches on zero-shot event detection usually train models on datasets annotated with known event types, and prompt them with unseen event definitions. These approaches yield sporadic successes, yet generally fall short of expectations. In this work, we aim to improve zero-shot event detection by training models to better follow event definitions. We hypothesize that a diverse set of event types and definitions are the key for models to learn to follow event definitions while …

abstract aim arxiv cs.cl datasets definition definitions detection event prompt them train training training models type types work zero-shot