Structure Regularized Bidirectional Recurrent Convolutional Neural Network for Relation Classification
This work addresses relation classification in NLP, specifically for Chinese text, with incremental improvements through structure regularization.
The paper tackles relation classification by proposing a Structure Regularized Bidirectional Recurrent Convolutional Neural Network (SR-BRCNN) that leverages dependency relations in the shortest dependency path, improving the F1 score by 10.3 on a new Chinese dataset and matching state-of-the-art on an existing benchmark.
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.