Closed michelole closed 5 years ago
We need a baseline to compare our submitted NN results with.
Therefore, reintroduce our LSTMClassifier, but now using BioSentVec embeddings obtained in #79 to overcome out-of-vocabulary issues.
LSTMClassifier
Use also the same tokenizer as used to generate embeddings in #79 (to be done in #118).
Fixed by https://github.com/bst-mug/n2c2/pull/109.
We need a baseline to compare our submitted NN results with.
Therefore, reintroduce our
LSTMClassifier
, but now using BioSentVec embeddings obtained in #79 to overcome out-of-vocabulary issues.Use also the same tokenizer as used to generate embeddings in #79 (to be done in #118).