def tagged_parse(self, sentence, verbose=False):
"""
Use MaltParser to parse a sentence. Takes a sentence as a list of
(word, tag) tuples; the sentence must have already been tokenized and
tagged.
@param sentence: Input sentence to parse
@type sentence: L{list} of (word, tag) L{tuple}s.
@return: C{DependencyGraph} the dependency graph representation of the sentence
"""
if not self._malt_bin:
raise Exception(
"MaltParser location is not configured. Call config_malt() first."
)
if not self._trained:
raise Exception(
"Parser has not been trained. Call train() first.")
input_file = os.path.join(tempfile.gettempdir(), 'malt_input.conll')
output_file = os.path.join(tempfile.gettempdir(), 'malt_output.conll')
execute_string = 'java -jar %s -w %s -c %s -i %s -o %s -m parse'
if not verbose:
execute_string += ' > ' + os.path.join(tempfile.gettempdir(),
"malt.out")
f = None
try:
f = open(input_file, 'w')
for (i, (word, tag)) in enumerate(sentence):
f.write('%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\n' %
(i + 1, word, '_', tag, tag, '_', '0', 'a', '_', '_'))
f.write('\n')
f.close()
cmd = [
'java',
'-jar %s' % self._malt_bin,
'-w %s' % tempfile.gettempdir(),
'-c %s' % self.mco,
'-i %s' % input_file,
'-o %s' % output_file, '-m parse'
]
self._execute(cmd, 'parse', verbose)
return DependencyGraph.load(output_file)
finally:
if f: f.close()
def tagged_parse(self, sentence, verbose=False):
"""
Use MaltParser to parse a sentence. Takes a sentence as a list of
(word, tag) tuples; the sentence must have already been tokenized and
tagged.
@param sentence: Input sentence to parse
@type sentence: L{list} of (word, tag) L{tuple}s.
@return: C{DependencyGraph} the dependency graph representation of the sentence
"""
if not self._malt_bin:
raise Exception("MaltParser location is not configured. Call config_malt() first.")
if not self._trained:
raise Exception("Parser has not been trained. Call train() first.")
input_file = os.path.join(tempfile.gettempdir(), 'malt_input.conll')
output_file = os.path.join(tempfile.gettempdir(), 'malt_output.conll')
execute_string = 'java -jar %s -w %s -c %s -i %s -o %s -m parse'
if not verbose:
execute_string += ' > ' + os.path.join(tempfile.gettempdir(), "malt.out")
f = None
try:
f = open(input_file, 'w')
for (i, (word,tag)) in enumerate(sentence):
f.write('%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\n' %
(i+1, word, '_', tag, tag, '_', '0', 'a', '_', '_'))
f.write('\n')
f.close()
cmd = ['java', '-jar %s' % self._malt_bin, '-w %s' % tempfile.gettempdir(),
'-c %s' % self.mco, '-i %s' % input_file, '-o %s' % output_file, '-m parse']
self._execute(cmd, 'parse', verbose)
return DependencyGraph.load(output_file)
finally:
if f: f.close()
