Aligning Script Events with Narrative Texts

TL;DR

This paper introduces a new task of aligning script events in narrative texts with rich script event representations, demonstrating its feasibility through a model that leverages linguistic and temporal information.

Contribution

It proposes a novel task of mapping narrative event mentions to script event types and presents a model that effectively utilizes linguistic and temporal cues.

Findings

The task of aligning script events with narrative texts is feasible.

The proposed model successfully exploits linguistic and temporal information.

Experimental results validate the approach's effectiveness.

Abstract

Script knowledge plays a central role in text understanding and is relevant for a variety of downstream tasks. In this paper, we consider two recent datasets which provide a rich and general representation of script events in terms of paraphrase sets. We introduce the task of mapping event mentions in narrative texts to such script event types, and present a model for this task that exploits rich linguistic representations as well as information on temporal ordering. The results of our experiments demonstrate that this complex task is indeed feasible.