Structure Regularized Bidirectional Recurrent Convolutional Neural Network for Relation Classification

TL;DR

This paper introduces SR-BRCNN, a novel neural network model that leverages structure regularization and dependency relations to improve relation classification in Chinese Sanwen and other datasets.

Contribution

The paper proposes a structure regularized bidirectional recurrent convolutional neural network that effectively utilizes dependency relations for relation classification, reducing model complexity and improving accuracy.

Findings

Outperforms state-of-the-art on Chinese Sanwen dataset

Achieves a 10.3 increase in F1 score

Performs comparably on SemEval-2010 Task 8

Abstract

Relation classification is an important semantic processing task in the field of natural language processing (NLP). In this paper, we present a novel model, Structure Regularized Bidirectional Recurrent Convolutional Neural Network(SR-BRCNN), to classify the relation of two entities in a sentence, and the new dataset of Chinese Sanwen for named entity recognition and relation classification. Some state-of-the-art systems concentrate on modeling the shortest dependency path (SDP) between two entities leveraging convolutional or recurrent neural networks. We further explore how to make full use of the dependency relations information in the SDP and how to improve the model by the method of structure regularization. We propose a structure regularized model to learn relation representations along the SDP extracted from the forest formed by the structure regularized dependency tree, which benefits reducing the complexity of the whole model and helps improve the $F_{1}$ score by 10.3. Experimental results show that our method outperforms the state-of-the-art approaches on the Chinese Sanwen task and performs as well on the SemEval-2010 Task 8 dataset\footnote{The Chinese Sanwen corpus this paper developed and used will be released in the further.