Improving Event Representation via Simultaneous Weakly Supervised Contrastive Learning and Clustering

TL;DR

This paper introduces SWCC, a novel framework combining weakly supervised contrastive learning and clustering to improve event representations by leveraging event co-occurrence and semantic relations.

Contribution

SWCC is the first to integrate simultaneous weakly supervised contrastive learning with prototype-based clustering for event representation learning.

Findings

SWCC outperforms baselines on similarity tasks.

Prototype vectors capture event relations.

Effective use of co-occurrence information.

Abstract

Representations of events described in text are important for various tasks. In this work, we present SWCC: a Simultaneous Weakly supervised Contrastive learning and Clustering framework for event representation learning. SWCC learns event representations by making better use of co-occurrence information of events. Specifically, we introduce a weakly supervised contrastive learning method that allows us to consider multiple positives and multiple negatives, and a prototype-based clustering method that avoids semantically related events being pulled apart. For model training, SWCC learns representations by simultaneously performing weakly supervised contrastive learning and prototype-based clustering. Experimental results show that SWCC outperforms other baselines on Hard Similarity and Transitive Sentence Similarity tasks. In addition, a thorough analysis of the prototype-based clustering method demonstrates that the learned prototype vectors are able to implicitly capture various relations between events.