Seq2seq NMT tutorial needs refactoring

[seanpmorgan]

Per the email from TF-Docs team:
https://groups.google.com/a/tensorflow.org/forum/#!topic/addons/F6MrrMfVVBA

This notebook is failing for:

nbconvert.preprocessors.execute.CellExecutionError: An error occurred while executing the following cell:
------------------
# load dataset
filename = 'deu.txt' #change filename if necessary
doc = load_documnet(filename)

#clean sentences and save clean data
pairs = doc_sep_pair(doc)
clean_sentences = clean_sentences(pairs)
# uncomment to check mapping
#for i in range(100):
#	print('[%s] => [%s]' % (clean_sentences[i,0], clean_sentences[i,1]))
------------------

---------------------------------------------------------------------------
FileNotFoundError                         Traceback (most recent call last)
 in 
      1 # load dataset
      2 filename = 'deu.txt' #change filename if necessary
----> 3 doc = load_documnet(filename)
      4 
      5 #clean sentences and save clean data

 in load_documnet(filename)
      2 def load_documnet(filename):
      3         # open the file as read only
----> 4         file = open(filename, mode='rt', encoding='utf-8')
      5         # read all text
      6         text = file.read()

FileNotFoundError: [Errno 2] No such file or directory: 'deu.txt'
FileNotFoundError: [Errno 2] No such file or directory: 'deu.txt'

[seanpmorgan]

Seperately as @john-8704 noted in #806 this tutorial doesn't utilize the seq2seq subpackage in TFA. It should be rebuilt to showcase how to use it. If it helps some sample code can be found here:
https://github.com/tensorflow/addons/tree/master/tensorflow_addons/seq2seq#sample-code-and-migration-guide-from-tf-1x

cc @Om-Pandey

[Om-Pandey]

@seanpmorgan I looked into the issue, seems like I didn't add the seq2seq package from TFA, the dataset issue though I think is some kind of an environment refreshing problem cause it is working just fine on my end, I ran it 15-16 times, seems neat.... I was trying to do the tfa.seq2seq but I am running into #676 .. please tell me if there is any way to go about this, meanwhile, I will try other options.