Cross-Task Instance Representation Interactions and Label Dependencies for Joint Information Extraction with Graph Convolutional Networks

TL;DR

This paper introduces FourIE, a novel deep learning model that jointly performs four information extraction tasks by leveraging inter-task dependencies at representation and label levels, achieving state-of-the-art results.

Contribution

The paper presents a new model that captures inter-task dependencies using interaction and dependency graphs, enhancing joint information extraction performance.

Findings

Achieves state-of-the-art results on monolingual and multilingual IE tasks.

Effectively models inter-task dependencies at representation and label levels.

Improves prediction accuracy through a novel regularization mechanism.

Abstract

Existing works on information extraction (IE) have mainly solved the four main tasks separately (entity mention recognition, relation extraction, event trigger detection, and argument extraction), thus failing to benefit from inter-dependencies between tasks. This paper presents a novel deep learning model to simultaneously solve the four tasks of IE in a single model (called FourIE). Compared to few prior work on jointly performing four IE tasks, FourIE features two novel contributions to capture inter-dependencies between tasks. First, at the representation level, we introduce an interaction graph between instances of the four tasks that is used to enrich the prediction representation for one instance with those from related instances of other tasks. Second, at the label level, we propose a dependency graph for the information types in the four IE tasks that captures the connections between the types expressed in an input sentence. A new regularization mechanism is introduced to enforce the consistency between the golden and predicted type dependency graphs to improve representation learning. We show that the proposed model achieves the state-of-the-art performance for joint IE on both monolingual and multilingual learning settings with three different languages.