def rank_query_candidates(self, query_candidates, key=lambda x: x, utterance=""):
"""
Returns the candidate generated from search results. This methods doesn't look into the
existing candidates, but rather creates a new one based on search results.
:param query_candidates: List of EvaluationCandidate objects. This answerer don't actually use them.
"""
if isinstance(utterance, unicode):
utterance = utterance.encode('utf-8')
if utterance in self._answers_cache:
return self._answers_cache[utterance]
question_entities = set([e['name'] for e in find_entity_mentions(utterance.encode("utf-8"), use_tagme=True)])
res = self._searcher.search(utterance, topn=self._topn)
res = json.loads(res)
entities = dict()
for r in res:
for e in r['entities']:
if e['mid'] not in entities:
entities[e['mid']] = []
entities[e['mid']].append((r['phrase'], r['score']))
answers = sorted(entities.items(), key=lambda x: sum(score for _, score in x[1]), reverse=True)
answers = [(KBEntity.get_entity_name(answer[0].replace("/", ".")), answer[1]) for answer in answers
if answer[0] not in question_entities]
answers = [EvaluationCandidate(None, answer[1], [answer[0], ]) for answer in answers]
self._answers_cache[utterance] = answers
return answers
with open("type-model.pickle", 'wb') as out:
pickle.dump((vec, type_scorer), out)
if __name__ == "__main__":
extract_npmi_ngram_type_pairs()
exit()
globals.read_configuration('config.cfg')
parser = globals.get_parser()
scorer_globals.init()
datasets = ["webquestions_split_train", ]
# datasets = ["webquestions_split_train_externalentities", "webquestions_split_dev_externalentities",]
# datasets = ["webquestions_split_train_externalentities3", "webquestions_split_dev_externalentities3",]
data = []
for dataset in datasets:
queries = load_eval_queries(dataset)
for index, query in enumerate(queries):
tokens = [token.token for token in parser.parse(query.utterance).tokens]
answer_entities = [mid for answer in query.target_result
for mid in KBEntity.get_entityid_by_name(answer, keep_most_triples=True)]
notable_types = [KBEntity.get_notable_type(entity_mid) for entity_mid in answer_entities]
data.append((tokens, notable_types))
logger.info(tokens)
logger.info([KBEntity.get_entity_name(notable_type) for notable_type in notable_types])
with open("question_tokens_notable_types.pickle", 'wb') as out:
pickle.dump(data, out)
