Untokenize. Brought to you by Python.

When writing IQABOT (see here) I needed to undo the tokenization of a rewritten query. Below is the code for a very simple Python function to “untokenize” some text.

def untokenize(sent):
     untok = ""
     punc = ['.',',','?'] # Add more punctuation
     for tok in sent:
          if tok in punc:
               untok += tok
               untok += " "+tok

return untok.lstrip()
This entry was posted in NLP, Python. Bookmark the permalink.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s