Named Entity Recognition With Parallel Recurrent Neural Networks

Code

• github.com/speedcell4/UOI-P18-2012
  none★ 0

Abstract

We present a new architecture for named entity recognition. Our model employs multiple independent bidirectional LSTM units across the same input and promotes diversity among them by employing an inter-model regularization term. By distributing computation across multiple smaller LSTMs we find a significant reduction in the total number of parameters. We find our architecture achieves state-of-the-art performance on the CoNLL 2003 NER dataset.

Tasks

Reproductions