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

## TL;DR

This paper introduces a neural network model that jointly extracts entities and their relations using a deep biaffine attention mechanism, achieving state-of-the-art results on the CoNLL04 dataset without relying on handcrafted features.

## Contribution

The novel contribution is extending a BiLSTM-CRF model with a deep biaffine attention layer to model second-order interactions for relation classification.

## Key findings

- Outperforms previous models on CoNLL04 dataset
- Achieves new state-of-the-art performance
- Does not require handcrafted features

## 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.