Copynet-tf

Improvements
- Bumped to `TensorFlow 2.2.0`
- Decoder refactored to be used with default Keras `fit predict` pipeline
- Example updated to show usage with Keras pipeline
- Per-epoch training time on toy example decreased to `4s` from `11s`

Limitation
- Tested with `tf.data.Dataset` only
- Need to pass `drop_remainder=True` to `batch()` method of `tf.data.Dataset`. Cannot handle case of unknown `batch_size`

- Beam search is improvised to give more variance in predictions
- Bug with copy token fixed

- Decoder correctly masks special tokens while copying now
- BeamSearch stops adding to probability after end token

bug: fix not copying special tokens

add reporting attentive and selective weights while calculating loss

- add option to specify length in transform