For this problem, we proposed the use of bidirectional-LSTM’s(Long Short Term Memory) with 1-D CNN layer to classify patient notes at character level and at word level. The 1-D CNN is employed to scale back the training time. In order to improve the performance, we will also feed the network combined word embedding consisting of Pre-trained word2vec 100 dimension word embedding trained on the Twitter ADR Dataset database and character embedding generated by a Char-CNN for Named Entity Recognition
-
Notifications
You must be signed in to change notification settings - Fork 6
For this problem, we proposed the use of bidirectional-LSTM’s(Long Short Term Memory) with 1-D CNN layer to classify patient notes at character level and at word level. The 1-D CNN is employed to scale back the training time. In order to improve the performance, we will also feed the network combined word embedding consisting of Pre-trained word…
sumanismcse/Extraction-of-Adverse-Drug-Reaction-from-Unstructured-Data-using-Bidirectional-LSTM-Network
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
For this problem, we proposed the use of bidirectional-LSTM’s(Long Short Term Memory) with 1-D CNN layer to classify patient notes at character level and at word level. The 1-D CNN is employed to scale back the training time. In order to improve the performance, we will also feed the network combined word embedding consisting of Pre-trained word…
Topics
deep-neural-networks
deep-learning
word2vec
machine-learning-algorithms
word-embeddings
extraction
named-entities
reactions
lstm
named-entity-recognition
lstm-model
lstm-neural-networks
bidirectional-lstm
cnn-text-classification
unstructured-data
pharmacovigilance
adverse-drug-reaction
drug-target-interactions