Whats New? Identifying the Unfolding of New Events in Narratives

TL;DR

This paper introduces a new task of identifying novel events in narratives, focusing on their information status and leveraging annotated datasets and baseline models for improved narrative comprehension.

Contribution

It defines the task of new event identification, creates an annotated dataset, and provides baseline models for narrative understanding.

Findings

Annotated a corpus for new event detection

Evaluated annotation quality and task difficulty

Provided baseline machine learning models

Abstract

Narratives include a rich source of events unfolding over time and context. Automatic understanding of these events provides a summarised comprehension of the narrative for further computation (such as reasoning). In this paper, we study the Information Status (IS) of the events and propose a novel challenging task: the automatic identification of new events in a narrative. We define an event as a triplet of subject, predicate, and object. The event is categorized as new with respect to the discourse context and whether it can be inferred through commonsense reasoning. We annotated a publicly available corpus of narratives with the new events at sentence level using human annotators. We present the annotation protocol and study the quality of the annotation and the difficulty of the task. We publish the annotated dataset, annotation materials, and machine learning baseline models for the task of new event extraction for narrative understanding.