End-to-End Neural Relation Extraction Using Deep Biaffine Attention [chapter]

Dat Quoc Nguyen, Karin Verspoor
2019 Lecture Notes in Computer Science  
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,
more » ... xperimental results show that our model outperforms previous models, producing new state-of-the-art performances.
doi:10.1007/978-3-030-15712-8_47 fatcat:ksjkna7qpba3labw5sefqmgtbu