Extensively Matching for Few-shot Learning Event Detection

TL;DR

This paper formulates event detection as a few-shot learning problem, introducing two novel loss factors that improve model generalization to new event types, demonstrated through extensive experiments on ACE-2005.

Contribution

It proposes a new few-shot learning framework for event detection with two novel loss factors that enhance training signals and generalization.

Findings

Improved performance on ACE-2005 dataset in few-shot settings

Effective application of the loss factors across metric-based models

Enhanced ability to detect new event types with limited examples

Abstract

Current event detection models under super-vised learning settings fail to transfer to newevent types. Few-shot learning has not beenexplored in event detection even though it al-lows a model to perform well with high gener-alization on new event types. In this work, weformulate event detection as a few-shot learn-ing problem to enable to extend event detec-tion to new event types. We propose two novelloss factors that matching examples in the sup-port set to provide more training signals to themodel. Moreover, these training signals can beapplied in many metric-based few-shot learn-ing models. Our extensive experiments on theACE-2005 dataset (under a few-shot learningsetting) show that the proposed method can im-prove the performance of few-shot learning