Combining Neural Networks and Log-linear Models to Improve Relation Extraction

Abstract

The last decade has witnessed the success of the traditional feature-based method on exploiting the discrete structures such as words or lexical patterns to extract relations from text. Recently, convolutional and recurrent neural networks has provided very effective mechanisms to capture the hidden structures within sentences via continuous representations, thereby significantly advancing the performance of relation extraction. The advantage of convolutional neural networks is their capacity to generalize the consecutive k-grams in the sentences while recurrent neural networks are effective to encode long ranges of sentence context. This paper proposes to combine the traditional feature-based method, the convolutional and recurrent neural networks to simultaneously benefit from their advantages. Our systematic evaluation of different network architectures and combination methods demonstrates the effectiveness of this approach and results in the state-of-the-art performance on the ACE 2005 and SemEval dataset.

References in corpus (5)

• Improving neural networks by preventing co-adaptation of feature detectors
• ADADELTA: An Adaptive Learning Rate Method
• On the difficulty of training Recurrent Neural Networks
• A Convolutional Neural Network for Modelling Sentences
• Classifying Relations by Ranking with Convolutional Neural Networks

Cited by in corpus (23)

• Improved Relation Classification by Deep Recurrent Neural Networks with Data Augmentation
• End-to-end neural relation extraction using deep biaffine attention
• More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction
• A Discourse-Level Named Entity Recognition and Relation Extraction Dataset for Chinese Literature Text
• Learning for Biomedical Information Extraction: Methodological Review of Recent Advances
• A Survey on Deep Learning Toolkits and Libraries for Intelligent User Interfaces
• Heterogeneous Supervision for Relation Extraction: A Representation Learning Approach
• Extracting Multiple-Relations in One-Pass with Pre-Trained Transformers
• Improving Hypernymy Detection with an Integrated Path-based and Distributional Method
• A Study of Recent Contributions on Information Extraction
• Multi-labeled Relation Extraction with Attentive Capsule Network
• Transfer Learning for Relation Extraction via Relation-Gated Adversarial Learning
• Structure Regularized Bidirectional Recurrent Convolutional Neural Network for Relation Classification
• Dialogue-Based Relation Extraction
• Cross-Lingual Relation Extraction with Transformers
• Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control
• Knowledge Base Relation Detection via Multi-View Matching
• Relation Adversarial Network for Low Resource Knowledge Graph Completion
• Natural Language Processing for EHR-Based Computational Phenotyping
• A bag-of-concepts model improves relation extraction in a narrow knowledge domain with limited data
• Enriched Attention for Robust Relation Extraction
• REflex: Flexible Framework for Relation Extraction in Multiple Domains
• On the Effectiveness of the Pooling Methods for Biomedical Relation Extraction with Deep Learning