CNN Bidirectional LSTM

Introduced by Chiu et al. in Named Entity Recognition with Bidirectional LSTM-CNNs

A CNN BiLSTM is a hybrid bidirectional LSTM and CNN architecture. In the original formulation applied to named entity recognition, it learns both character-level and word-level features. The CNN component is used to induce the character-level features. For each word the model employs a convolution and a max pooling layer to extract a new feature vector from the per-character feature vectors such as character embeddings and (optionally) character type.

Source: Named Entity Recognition with Bidirectional LSTM-CNNs

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Named Entity Recognition	6	16.67%
Dependency Parsing	2	5.56%
Feature Engineering	2	5.56%
Person Re-Identification	1	2.78%
Earthquake prediction	1	2.78%
Time Series Forecasting	1	2.78%
Voice Query Recognition	1	2.78%
Sign Language Recognition	1	2.78%
Intent Classification	1	2.78%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
BiLSTM	Bidirectional Recurrent Neural Networks
Convolution	Convolutions

Categories

Add Remove

Bidirectional Recurrent Neural Networks