Semi-supervised New Event Type Induction and Description via Contrastive Loss-Enforced Batch Attention

TL;DR

This paper introduces a semi-supervised method for discovering and describing new event types using a contrastive loss and attention mechanism, significantly improving clustering quality and enabling type naming and linking to FrameNet.

Contribution

It proposes a novel contrastive loss-based approach for event type induction that enhances clustering and supports type description and FrameNet linking.

Findings

Normalized mutual information increased by over 20%.

Fowlkes-Mallows scores improved by over 20%.

Method enables type naming and linking to FrameNet.

Abstract

Most event extraction methods have traditionally relied on an annotated set of event types. However, creating event ontologies and annotating supervised training data are expensive and time-consuming. Previous work has proposed semi-supervised approaches which leverage seen (annotated) types to learn how to automatically discover new event types. State-of-the-art methods, both semi-supervised or fully unsupervised, use a form of reconstruction loss on specific tokens in a context. In contrast, we present a novel approach to semi-supervised new event type induction using a masked contrastive loss, which learns similarities between event mentions by enforcing an attention mechanism over the data minibatch. We further disentangle the discovered clusters by approximating the underlying manifolds in the data, which allows us to increase normalized mutual information and Fowlkes-Mallows scores by over 20% absolute. Building on these clustering results, we extend our approach to two new tasks: predicting the type name of the discovered clusters and linking them to FrameNet frames.