A Graph Enhanced BERT Model for Event Prediction

TL;DR

This paper introduces a novel BERT-based model that automatically constructs event graphs to improve event prediction accuracy, addressing the limitations of sparse relational data in previous methods.

Contribution

The proposed method integrates event graph construction within BERT using a structured variable, enabling better prediction of event relationships for unseen data.

Findings

Outperforms state-of-the-art baselines on script event prediction.

Effective in predicting event connections for unseen events.

Enhances event prediction accuracy through automatic graph building.

Abstract

Predicting the subsequent event for an existing event context is an important but challenging task, as it requires understanding the underlying relationship between events. Previous methods propose to retrieve relational features from event graph to enhance the modeling of event correlation. However, the sparsity of event graph may restrict the acquisition of relevant graph information, and hence influence the model performance. To address this issue, we consider automatically building of event graph using a BERT model. To this end, we incorporate an additional structured variable into BERT to learn to predict the event connections in the training process. Hence, in the test process, the connection relationship for unseen events can be predicted by the structured variable. Results on two event prediction tasks: script event prediction and story ending prediction, show that our approach can outperform state-of-the-art baseline methods.