If not using POS feature to dependency, error occurred.

[changukshin]

taggers.py
def parse_sentence(self, tokens):

    if self.use_pos:
        tokens = self.pos_tagger.tag_tokens(tokens, return_tokens=True)
    #if not using pos. tokens are not tuple.
    for token in tokens:
        if self.use_pos:
            word, pos = token
        else:
            pos = None
        #if not using pos, word is referenced before assignment
        tokens_obj.append(attributes.Token(word, pos=pos)) 

Here is my traceback

PC:2016_NLPNET user$ python bin/nlpnet-tag.py dependency
It was home.
Traceback (most recent call last):
  File "bin/nlpnet-tag.py", line 120, in <module>
    interactive_running(args)
  File "bin/nlpnet-tag.py", line 48, in interactive_running
    result = tagger.tag(text)
  File "/Users/username/anaconda/lib/python2.7/site-packages/nlpnet/taggers.py", line 398, in tag
    return self.parse(text)
  File "/Users/username/anaconda/lib/python2.7/site-packages/nlpnet/taggers.py", line 336, in parse
    parsed = self.parse_sentence(sent)
  File "/Users/username/anaconda/lib/python2.7/site-packages/nlpnet/taggers.py", line 369, in parse_sentence
    tokens_obj.append(attributes.Token(word, pos=pos))
UnboundLocalError: local variable 'word' referenced before assignment

[erickrf]

Sorry for the delay, I haven't had much time to look at nlpnet, but I'll try to check it this week.