Improved Relation Classification by Deep Recurrent Neural Networks with Data Augmentation

Abstract

Nowadays, neural networks play an important role in the task of relation classification. By designing different neural architectures, researchers have improved the performance to a large extent in comparison with traditional methods. However, existing neural networks for relation classification are usually of shallow architectures (e.g., one-layer convolutional neural networks or recurrent networks). They may fail to explore the potential representation space in different abstraction levels. In this paper, we propose deep recurrent neural networks (DRNNs) for relation classification to tackle this challenge. Further, we propose a data augmentation method by leveraging the directionality of relations. We evaluated our DRNNs on the SemEval-2010 Task~8, and achieve an F1-score of 86.1%, outperforming previous state-of-the-art recorded results.

Accepted by COLING-16

References in corpus (3)

• Classifying Relations by Ranking with Convolutional Neural Networks
• Combining Neural Networks and Log-linear Models to Improve Relation Extraction
• Discriminative Neural Sentence Modeling by Tree-Based Convolution

Cited by in corpus (21)

• Data Augmentation Approaches in Natural Language Processing: A Survey
• Label Refinery: Improving ImageNet Classification through Label Progression
• Data Augmentation in Natural Language Processing: A Novel Text Generation Approach for Long and Short Text Classifiers
• Classifying medical relations in clinical text via convolutional neural networks
• Automatic identification of fossils and abiotic grains during carbonate microfacies analysis using deep convolutional neural networks
• Natural Language Inference by Tree-Based Convolution and Heuristic Matching
• More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction
• Word Embedding Perturbation for Sentence Classification
• Deep Neural Networks for Pattern Recognition
• Learning for Biomedical Information Extraction: Methodological Review of Recent Advances
• CAD2Render: A Modular Toolkit for GPU-accelerated Photorealistic Synthetic Data Generation for the Manufacturing Industry
• Improving Hypernymy Detection with an Integrated Path-based and Distributional Method
• Influence-guided Data Augmentation for Neural Tensor Completion
• Domain adaptation for holistic skin detection
• SeismoGen: Seismic Waveform Synthesis Using Generative Adversarial Networks
• CIS-Net: A Novel CNN Model for Spatial Image Steganalysis via Cover Image Suppression
• A Walk-based Model on Entity Graphs for Relation Extraction
• On the Role of Supervision in Unsupervised Constituency Parsing
• LSTM and GPT-2 Synthetic Speech Transfer Learning for Speaker Recognition to Overcome Data Scarcity
• Indirect Supervision for Relation Extraction using Question-Answer Pairs
• REflex: Flexible Framework for Relation Extraction in Multiple Domains