A Boundary Determined Neural Model for Relation Extraction

Abstract

Existing models extract entity relations only after two entity spans have been precisely extracted that influenced the performance of relation extraction. Compared with recognizing entity spans, because the boundary has a small granularity and a less ambiguity, it can be detected precisely and incorporated to learn better representation. Motivated by the strengths of boundary, we propose a boundary determined neural (BDN) model, which leverages boundaries as task-related cues to predict the relation labels. Our model can predict high-quality relation instance via the pairs of boundaries, which can relieve error propagation problem. Moreover, our model fuses with boundary-relevant information encoding to represent distributed representation to improve the ability of capturing semantic and dependency information, which can increase the discriminability of neural network. Experiments show that our model achieves state-of-the-art performances on ACE05 corpus.