Constructing Narrative Event Evolutionary Graph for Script Event Prediction

TL;DR

This paper introduces a novel narrative event evolutionary graph and a scaled graph neural network to improve script event prediction by better utilizing event network information, significantly outperforming existing methods.

Contribution

The paper proposes constructing a narrative event evolutionary graph from news data and a scaled graph neural network for improved event prediction, addressing limitations of previous pairwise models.

Findings

Significant performance improvement over baseline methods.

Effective modeling of event evolution patterns.

Scalable approach for large event graphs.

Abstract

Script event prediction requires a model to predict the subsequent event given an existing event context. Previous models based on event pairs or event chains cannot make full use of dense event connections, which may limit their capability of event prediction. To remedy this, we propose constructing an event graph to better utilize the event network information for script event prediction. In particular, we first extract narrative event chains from large quantities of news corpus, and then construct a narrative event evolutionary graph (NEEG) based on the extracted chains. NEEG can be seen as a knowledge base that describes event evolutionary principles and patterns. To solve the inference problem on NEEG, we present a scaled graph neural network (SGNN) to model event interactions and learn better event representations. Instead of computing the representations on the whole graph, SGNN processes only the concerned nodes each time, which makes our model feasible to large-scale graphs. By comparing the similarity between input context event representations and candidate event representations, we can choose the most reasonable subsequent event. Experimental results on widely used New York Times corpus demonstrate that our model significantly outperforms state-of-the-art baseline methods, by using standard multiple choice narrative cloze evaluation.