End-to-end neural relation extraction using deep biaffine attention

Abstract

We propose a neural network model for joint extraction of named entities and relations between them, without any hand-crafted features. The key contribution of our model is to extend a BiLSTM-CRF-based entity recognition model with a deep biaffine attention layer to model second-order interactions between latent features for relation classification, specifically attending to the role of an entity in a directional relationship. On the benchmark "relation and entity recognition" dataset CoNLL04, experimental results show that our model outperforms previous models, producing new state-of-the-art performances.

Proceedings of the 41st European Conference on Information Retrieval (ECIR 2019), to appear

References in corpus (4)

• Adam: A Method for Stochastic Optimization
• Joint entity recognition and relation extraction as a multi-head selection problem
• DyNet: The Dynamic Neural Network Toolkit
• Combining Neural Networks and Log-linear Models to Improve Relation Extraction

Cited by in corpus (8)

• Span-based Joint Entity and Relation Extraction with Transformer Pre-training
• Deep Neural Approaches to Relation Triplets Extraction: A Comprehensive Survey
• End-to-end Named Entity Recognition and Relation Extraction using Pre-trained Language Models
• MatSciRE: Leveraging Pointer Networks to Automate Entity and Relation Extraction for Material Science Knowledge-base Construction
• Understanding Clinical Trial Reports: Extracting Medical Entities and Their Relations
• Deep Neural Networks for Relation Extraction
• Analyzing Vietnamese Legal Questions Using Deep Neural Networks with Biaffine Classifiers
• A Data Bootstrapping Recipe for Low Resource Multilingual Relation Classification