def addPossibleWordSensesToDBs(self, *dbs):
'''
Adds to the databases dbs all possible word senses (and fuzzy meanings)
based on their part of speech.
'''
wordnet = WordNet()
for db in dbs:
word2senses = defaultdict(list)
logger.info(db.mln.domains['concept'])
for res in db.query('has_pos(?word,?pos)'):
word_const = res['?word']
pos = POS_MAP.get(res['?pos'], None)
if pos is None:
continue
word = word_const.split('-')[0]
for i, synset in enumerate(wordnet.synsets(word, pos)):
sense_id = '%s-%.2d' % (word_const, i + 1)
word2senses[word_const].append(sense_id)
for concept in db.mln.domains['concept']:
sim = wordnet.semilarity(synset, concept)
db << ('is_a(%s,%s)' % (sense_id, concept), sim)
for word in word2senses:
for word2, senses in word2senses.iteritems():
if word2 == word:
continue
else:
for s in senses:
db << ('!has_sense(%s,%s)' % (word, s))
def addFuzzyEvidenceToDBs(self, *dbs):
'''
Adds to the databases dbs all fuzzy 'is_a' relationships
for all senses contained in the DB and in the MLN.
(has side effects on the original one)
'''
mln_domains = dbs[0].domains
domains_full = mergedom(mln_domains, *[db.domains for db in dbs])
concepts = domains_full['concept']
wordnet = WordNet()
for db in dbs:
for res in db.query('is_a(?sense, ?concept)'):
sense = res['?sense']
concept = res['?concept']
for c in concepts:
similarity = wordnet.semilarity(concept, c)
logger.info('{} ~ {} = {:.2f}'.format(
concept, c, similarity))
db << ('is_a({},{})'.format(sense, c), similarity)
return dbs