triples = list()
root = objectify.Element("frameinstances")
for filename in documents:
frame_instance_triples = list()
# read file
log.info("opening file {0}".format(filename))
with open(filename, 'r') as f:
text = f.read()
# semantic parsing
if config.get('semantics', 'module') == 'boxer':
# tokenization
if not options.tokenized:
log.info("Tokenization with t")
tokens = candc.tokenize(text)
if not tokens:
log.error("error during tokenization of file '{0}', exiting".format(filename))
continue
tokenized = "\n".join([' '.join(sentence) for sentence in tokens[:-1]])
else:
tokenized = text
log.info("Parsing with Boxer")
semantics = candc.get_all(tokenized)
if not semantics:
log.error("error during the execution of Boxer on file '{0}', exiting".format(filename))
continue
elif config.get('semantics', 'module') == 'semafor':
else:
output_format = options.format
triples = list()
frame_instance_triples = list()
root = objectify.Element("frameinstances")
for filename in documents:
# read file
log.info("opening file {0}".format(filename))
with open(filename) as f:
text = f.read()
# tokenization
if not options.tokenized:
log.info("Tokenization")
tokens = tokenize(text)
if not tokens:
log.error(
"error during tokenization of file '{0}', exiting".format(
filename))
continue
tokenized = "\n".join([' '.join(sentence) for sentence in tokens[:-1]])
else:
tokenized = text
log.info("Parsing")
drs = get_all(tokenized)
if not drs:
log.error("error during the execution of Boxer on file '{0}', exiting".
format(filename))
continue
output_format = options.format
triples = list()
frame_instance_triples = list()
root = objectify.Element("frameinstances")
for filename in documents:
# read file
log.info("opening file {0}".format(filename))
with open(filename) as f:
text = f.read()
# tokenization
if not options.tokenized:
log.info("Tokenization")
tokens = tokenize(text)
if not tokens:
log.error("error during tokenization of file '{0}', exiting".format(filename))
continue
tokenized = "\n".join([' '.join(sentence) for sentence in tokens[:-1]])
else:
tokenized = text
log.info("Parsing")
drs = get_all(tokenized)
if not drs:
log.error("error during the execution of Boxer on file '{0}', exiting".format(filename))
continue
log.info("Word sense disambiguation and entity linking")
synsets, entities = disambiguation(tokenized, drs)