def wordnet_dump():
out_file = args.output
mentions_file = args.mentions
logger.info('Loading mentions files...')
mentions = MentionData.read_mentions_json_to_mentions_data_list(mentions_file)
logger.info('Done loading mentions files, starting local dump creation...')
result_dump = dict()
wordnet = WordnetOnline()
for mention in mentions:
page = wordnet.get_pages(mention)
result_dump[page.orig_phrase] = page
with open(out_file, 'w') as out:
json.dump(result_dump, out, default=json_dumper)
logger.info('Wordnet Dump Created Successfully, '
'extracted total of %d wn pages', len(result_dump))
logger.info('Saving dump to file-%s', out_file)
def __init__(self, method: OnlineOROfflineMethod, wn_file: str = None):
"""
Extract Relation between two mentions according to Word Embedding cosine distance
Args:
method (required): OnlineOROfflineMethod.{ONLINE/OFFLINE} run against full wordnet or
a sub-set of it
wn_file (required on OFFLINE mode): str Location of wordnet subset file to work with
"""
logger.info('Loading Wordnet module')
self.connectivity = method
if self.connectivity == OnlineOROfflineMethod.ONLINE:
self.wordnet_impl = WordnetOnline()
elif self.connectivity == OnlineOROfflineMethod.OFFLINE:
self.wordnet_impl = WordnetOffline(wn_file)
logger.info('Wordnet module lead successfully')
super(WordnetRelationExtraction, self).__init__()
def __init__(self, method: OnlineOROfflineMethod, wn_file: str = None):
"""
Extract Relation between two mentions according to Word Embedding cosine distance
Args:
method (required): OnlineOROfflineMethod.{ONLINE/OFFLINE} run against full wordnet or
a sub-set of it
wn_file (required on OFFLINE mode): str Location of wordnet subset file to work with
"""
logger.info('Loading Wordnet module')
self.connectivity = method
if self.connectivity == OnlineOROfflineMethod.ONLINE:
self.wordnet_impl = WordnetOnline()
elif self.connectivity == OnlineOROfflineMethod.OFFLINE:
if wn_file is not None and os.path.isdir(wn_file):
self.wordnet_impl = WordnetOffline(wn_file)
else:
raise FileNotFoundError(
'WordNet resource directory not found or not in path')
logger.info('Wordnet module lead successfully')
super(WordnetRelationExtraction, self).__init__()