Maximilian Hofer

This parser might help you to tag your own data: `https://github.com/mxhofer/i2b2_2009-to-CoNLL/blob/master/parser.ipynb`. It parses i2b2 medical data to CoNLL format, which is used for this network architecture. It's very easy to...

Hello! That's correct. This is because the convolutional neural net (CNN) processes the padded character vectors of equal length. Alternatively, one could split the CNN input into equal-size batches (e.g....

The maximum length was chosen after analyzing word lengths in the documents, such that no words are cut off.

Padding is indeed applied to characters. For example, the padded character-level input below is for the word "RECORD". The output of the `padding(Sentences)` function is a list of documents of...

Parse the string to the CoNLL format, then store it as a text file and us it for inference. This code parses i2b2 medical text data to CoNLL and has...

Yes, same issue here. I tried to prepend `tensorflow.` to all the keras imports to use tensorflow instead of plain keras, but got the same error. tf version 2.3.0. shap...