Seeing the Forest and the Trees: Detection and Cross-Document Coreference Resolution of Militarized Interstate Disputes

TL;DR

This paper introduces a new dataset and a multi-task neural network model for detecting political events and linking related event references across multiple documents, advancing automated event analysis in political science.

Contribution

It provides the Headlines of War dataset for evaluating event detection and coreference, and proposes a neural network model capable of performing both tasks simultaneously.

Findings

The neural network effectively recognizes events and coreferences.

The dataset enables evaluation of cross-document event linking.

Model achieves promising accuracy on political event detection.

Abstract

Previous efforts to automate the detection of social and political events in text have primarily focused on identifying events described within single sentences or documents. Within a corpus of documents, these automated systems are unable to link event references -- recognize singular events across multiple sentences or documents. A separate literature in computational linguistics on event coreference resolution attempts to link known events to one another within (and across) documents. I provide a data set for evaluating methods to identify certain political events in text and to link related texts to one another based on shared events. The data set, Headlines of War, is built on the Militarized Interstate Disputes data set and offers headlines classified by dispute status and headline pairs labeled with coreference indicators. Additionally, I introduce a model capable of accomplishing both tasks. The multi-task convolutional neural network is shown to be capable of recognizing events and event coreferences given the headlines' texts and publication dates.