adding additional features for QA task

[telukuntla]

Hi,
my goal is to extract contextual word embeddings from last layer of BioBert and add additional features, before performing QA fine-tuning. please suggest me how to achieve this. also I found that when I print 'final_hidden = model.get_sequence_output()' to console, tensor shape is getting printed instead of contextual embeddings. yours suggestions are appreciated.

[jhyuklee]

Please see #23 for extracting features from BioBERT.
Thank you.