Reintroduce LSTM with BioWordVec embeddings

bst-mug / n2c2

Support code for participation at the 2018 n2c2 Shared-Task Track 1

https://n2c2.dbmi.hms.harvard.edu

Apache License 2.0

6 stars 4 forks source link

Closed michelole closed 5 years ago

michelole commented 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.

Use also the same tokenizer as used to generate embeddings in #79 (to be done in #118).

michelole commented 5 years ago