I run dragnn training script, the training result missing "segmenter" directory compared to pre-trained ParseySaurus model, which is available here. https://drive.google.com/file/d/0BxpbZGYVZsEeSFdrUnBNMUp1YzQ/view?usp=sharing the directory "segmenter" is must for the script https://github.com/tensorflow/models/blob/master/research/syntaxnet/examples/dragnn/interactive_text_analyzer.ipynb. Do you how to generate "segmenter" in the model?