Named Entity Recognition with Bidirectional LSTM-CNNs

NER Comments

Paper Link

Overview

Architecture

NER using LSTM and CNN

The architecture is very straight-forward (from above diagram). Append word embeddings, word feature and character embeddings from CNN. Pass this through LSTM and have a softmax for every token.

Using Lexicons in NER

Results

Using Lexicons in NER

Kaushik Rangadurai

Code. Learn. Explore

Share this post

Comments