One for All: Neural Joint Modeling of Entities and Events

TL;DR

This paper introduces a neural joint model that simultaneously predicts entities, event triggers, and arguments, improving event extraction accuracy by leveraging shared deep learning representations.

Contribution

It proposes a novel deep learning-based joint modeling approach for entities and events, surpassing previous methods that relied on discrete features and separate predictions.

Findings

Achieved state-of-the-art performance in event extraction

Demonstrated the effectiveness of shared deep representations

Improved robustness by jointly modeling entities and events

Abstract

The previous work for event extraction has mainly focused on the predictions for event triggers and argument roles, treating entity mentions as being provided by human annotators. This is unrealistic as entity mentions are usually predicted by some existing toolkits whose errors might be propagated to the event trigger and argument role recognition. Few of the recent work has addressed this problem by jointly predicting entity mentions, event triggers and arguments. However, such work is limited to using discrete engineering features to represent contextual information for the individual tasks and their interactions. In this work, we propose a novel model to jointly perform predictions for entity mentions, event triggers and arguments based on the shared hidden representations from deep learning. The experiments demonstrate the benefits of the proposed method, leading to the state-of-the-art performance for event extraction.