A Decoupling and Aggregating Framework for Joint Extraction of Entities and Relations

TL;DR

This paper introduces a novel joint extraction framework that decouples feature encoding into subject, object, and relation components, and employs aggregation strategies to improve entity and relation extraction accuracy.

Contribution

The paper presents a new model that decouples feature encoding for entities and relations and enhances interaction through aggregation strategies, addressing semantic differences and interaction limitations.

Findings

Outperforms previous state-of-the-art models

Effective fine-grained feature encoding

Improved information interaction strategies

Abstract

Named Entity Recognition and Relation Extraction are two crucial and challenging subtasks in the field of Information Extraction. Despite the successes achieved by the traditional approaches, fundamental research questions remain open. First, most recent studies use parameter sharing for a single subtask or shared features for both two subtasks, ignoring their semantic differences. Second, information interaction mainly focuses on the two subtasks, leaving the fine-grained informtion interaction among the subtask-specific features of encoding subjects, relations, and objects unexplored. Motivated by the aforementioned limitations, we propose a novel model to jointly extract entities and relations. The main novelties are as follows: (1) We propose to decouple the feature encoding process into three parts, namely encoding subjects, encoding objects, and encoding relations. Thanks to this, we are able to use fine-grained subtask-specific features. (2) We propose novel inter-aggregation and intra-aggregation strategies to enhance the information interaction and construct individual fine-grained subtask-specific features, respectively. The experimental results demonstrate that our model outperforms several previous state-of-the-art models. Extensive additional experiments further confirm the effectiveness of our model.