class SentAnswerer(Ranker):
"""Ranks based on a simple score of relation and entity matches."""
def __init__(self, name, topn=50, **kwargs):
Ranker.__init__(self, name, **kwargs)
answers_cache_file = globals.config.get('WebSearchAnswers', 'sentsearch-answers-cache')
self._answers_cache = shelve.open(answers_cache_file)
self._searcher = SentSearchApi()
self._topn = topn
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
def close(self):
self._searcher.close()
self._answers_cache.close()
def __init__(self, name, topn=50, **kwargs):
Ranker.__init__(self, name, **kwargs)
answers_cache_file = globals.config.get('WebSearchAnswers', 'sentsearch-answers-cache')
self._answers_cache = shelve.open(answers_cache_file)
self._searcher = SentSearchApi()
self._topn = topn
