def tag(self, text=None):
"""
Tags the given text.
:param text: a string or unicode object. Strings assumed to be utf-8
:returns: a list of lists (sentences with tokens).
Each sentence has (token, tag) tuples.
"""
result = []
if text:
tokens = utils.tokenize(text, clean=False)
for sent in tokens:
tags = self.tag_tokens(sent)
result.append(zip(sent, tags))
else:
# read tsv from stdin
sent = []
for line in sys.stdin:
line = line.decode('utf-8').strip()
if line:
sent.append(line.split()[0])
else:
#ipdb.set_trace()
tags = self.tag_tokens(sent)
result.append(zip(sent, tags))
sent = []
return result
def tag(self, text):
"""
Runs the SRL process on the given text.
:param text: unicode or str encoded in utf-8.
:returns: a list of SRLAnnotatedSentence objects
"""
tokens = utils.tokenize(text, self.language)
result = []
for sent in tokens:
tagged = self.tag_tokens(sent)
result.append(tagged)
return result
def tag(self, text):
"""
Tags the given text.
:param text: a string or unicode object. Strings assumed to be utf-8
:returns: a list of lists (sentences with tokens).
Each sentence has (token, tag) tuples.
"""
tokens = utils.tokenize(text, self.language)
result = []
for sent in tokens:
tagged = self.tag_tokens(sent, return_tokens=True)
result.append(tagged)
return result
def parse(self, text):
"""
Split the given text into sentences and determines their
dependency trees. If you want to provide your own tokenized
text, use `parse_sentence` instead.
:param text: a string
:returns: a list of ParsedSentence's
"""
sentences = utils.tokenize(text, self.language)
result = []
for sent in sentences:
parsed = self.parse_sentence(sent)
result.append(parsed)
return result