def get_entity_linker():
global _entity_linker
if _entity_linker is not None:
return _entity_linker
from entity_linker.entity_linker import EntityLinker, WebSearchResultsExtenderEntityLinker
_entity_linker = WebSearchResultsExtenderEntityLinker.init_from_config()
return _entity_linker
def get_number_of_external_entities():
import scorer_globals
globals.read_configuration('config_webentity.cfg')
parser = CoreNLPParser.init_from_config()
entity_linker = WebSearchResultsExtenderEntityLinker.init_from_config()
entity_linker.topn_entities = 100000
scorer_globals.init()
parameters = translator.TranslatorParameters()
parameters.require_relation_match = False
parameters.restrict_answer_type = False
datasets = ["webquestions_split_train", "webquestions_split_dev",]
# datasets = ["webquestions_split_train_externalentities", "webquestions_split_dev_externalentities",]
# datasets = ["webquestions_split_train_externalentities3", "webquestions_split_dev_externalentities3",]
external_entities_count = []
for dataset in datasets:
queries = load_eval_queries(dataset)
for index, query in enumerate(queries):
entities = entity_linker.identify_entities_in_tokens(parser.parse(query.utterance).tokens, text=query.utterance, find_dates=False)
print "-------------------------"
print query.utterance
print "\n".join(map(str, sorted(entities, key=lambda entity: entity.external_entity_count, reverse=True)))
external_entities_count.append(0)
for entity in entities:
if entity.external_entity:
external_entities_count[-1] += 1
if index % 100 == 0:
print >> sys.stderr, "%s queries processed" % index
print "========================================="
print external_entities_count
print sum(external_entities_count)
print len(external_entities_count)
