Deformable Stacked Structure for Named Entity Recognition
This work addresses a specific problem in natural language processing for researchers and practitioners, representing an incremental improvement over existing architectures.
The paper tackles named entity recognition by proposing a deformable stacked structure with dynamic connections between layers, achieving state-of-the-art performance on the OntoNotes dataset.
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.