Structure Regularized Neural Network for Entity Relation Classification for Chinese Literature Text

TL;DR

This paper introduces a new relation classification task for Chinese literature texts, proposing a novel neural network model that leverages dependency structures to improve accuracy significantly.

Contribution

The paper presents a new dataset and a structure regularized neural network model that enhances relation classification performance on Chinese literature texts.

Findings

F1 score improved by 10.3 points

Outperforms state-of-the-art methods

Effective use of dependency structures

Abstract

Relation classification is an important semantic processing task in the field of natural language processing. In this paper, we propose the task of relation classification for Chinese literature text. A new dataset of Chinese literature text is constructed to facilitate the study in this task. We present a novel model, named Structure Regularized Bidirectional Recurrent Convolutional Neural Network (SR-BRCNN), to identify the relation between entities. The proposed model learns relation representations along the shortest dependency path (SDP) extracted from the structure regularized dependency tree, which has the benefits of reducing the complexity of the whole model. Experimental results show that the proposed method significantly improves the F1 score by 10.3, and outperforms the state-of-the-art approaches on Chinese literature text.