A Large-Scale Exploration of Effective Global Features for a Joint Entity Detection and Tracking Model

TL;DR

This paper introduces a joint entity detection and tracking model that leverages large-scale global features, demonstrating their effectiveness in improving the understanding of entities in text beyond local features.

Contribution

The paper presents a novel joint EDT model that incorporates extensive global features, advancing beyond traditional local-feature-based approaches.

Findings

Global features significantly improve entity detection and tracking accuracy

Joint modeling of detection and coreference enhances overall performance

Complex non-local features are effective for EDT tasks

Abstract

Entity detection and tracking (EDT) is the task of identifying textual mentions of real-world entities in documents, extending the named entity detection and coreference resolution task by considering mentions other than names (pronouns, definite descriptions, etc.). Like NE tagging and coreference resolution, most solutions to the EDT task separate out the mention detection aspect from the coreference aspect. By doing so, these solutions are limited to using only local features for learning. In contrast, by modeling both aspects of the EDT task simultaneously, we are able to learn using highly complex, non-local features. We develop a new joint EDT model and explore the utility of many features, demonstrating their effectiveness on this task.