Recurrent Interaction Network for Jointly Extracting Entities and Classifying Relations

TL;DR

This paper introduces a recurrent interaction network that dynamically models explicit interactions between entity recognition and relation classification tasks, improving joint extraction performance.

Contribution

The paper proposes a novel recurrent interaction network for multi-task learning that explicitly models task interactions, unlike previous shared-network approaches.

Findings

The model outperforms existing methods on two real-world datasets.

Dynamic interaction modeling enhances joint extraction accuracy.

Empirical results confirm the effectiveness of the proposed approach.

Abstract

The idea of using multi-task learning approaches to address the joint extraction of entity and relation is motivated by the relatedness between the entity recognition task and the relation classification task. Existing methods using multi-task learning techniques to address the problem learn interactions among the two tasks through a shared network, where the shared information is passed into the task-specific networks for prediction. However, such an approach hinders the model from learning explicit interactions between the two tasks to improve the performance on the individual tasks. As a solution, we design a multi-task learning model which we refer to as recurrent interaction network which allows the learning of interactions dynamically, to effectively model task-specific features for classification. Empirical studies on two real-world datasets confirm the superiority of the proposed model.