Deformable Stacked Structure for Named Entity Recognition

TL;DR

This paper introduces a deformable stacked neural architecture for named entity recognition that dynamically connects layers, achieving state-of-the-art results on the OntoNotes dataset.

Contribution

It proposes a novel deformable stacked structure that dynamically establishes connections between layers in NER models, improving performance.

Findings

Achieves state-of-the-art performance on OntoNotes dataset.

Demonstrates effectiveness of dynamic layer connections.

Applicable to different layers in NER models.

Abstract

Neural architecture for named entity recognition has achieved great success in the field of natural language processing. Currently, the dominating architecture consists of a bi-directional recurrent neural network (RNN) as the encoder and a conditional random field (CRF) as the decoder. In this paper, we propose a deformable stacked structure for named entity recognition, in which the connections between two adjacent layers are dynamically established. We evaluate the deformable stacked structure by adapting it to different layers. Our model achieves the state-of-the-art performances on the OntoNotes dataset.