def test_sim_graph():
from sematch.semantic.graph import SimGraph
from sematch.semantic.similarity import WordNetSimilarity
from sematch.nlp import Extraction, lemmatization
from sematch.sparql import EntityFeatures
from collections import Counter
madrid = EntityFeatures().features('http://dbpedia.org/resource/Tom_Cruise')
words = Extraction().extract_words_sent(madrid['abstract'])
words = list(set(lemmatization(words)))
wns = WordNetSimilarity()
word_graph = SimGraph(words, wns.word_similarity)
word_scores = word_graph.page_rank()
words, scores =zip(*Counter(word_scores).most_common(10))
assert words is not None
def test_sim_graph():
from sematch.semantic.graph import SimGraph
from sematch.semantic.similarity import WordNetSimilarity
from sematch.nlp import Extraction, lemmatization
from sematch.sparql import EntityFeatures
from collections import Counter
madrid = EntityFeatures().features(
'http://dbpedia.org/resource/Tom_Cruise')
words = Extraction().extract_words_sent(madrid['abstract'])
words = list(set(lemmatization(words)))
wns = WordNetSimilarity()
word_graph = SimGraph(words, wns.word_similarity)
word_scores = word_graph.page_rank()
words, scores = zip(*Counter(word_scores).most_common(10))
assert words is not None
def disambiguate_graph(self, sentence):
words_origin = word_tokenize(sentence)
#extract words that have a synset in WordNet, currently support NOUN.
words = [w for w in words_origin if self._wn_sim.word2synset(w)]
# map words to synsets
words_synsets = {w:self._wn_sim.word2synset(w) for w in words}
# construct sets list
synsets = list(itertools.chain.from_iterable([words_synsets[w] for w in words]))
# remove duplicate synsets
synsets = list(set(synsets))
# define semantic similarity metric
sim_metric = lambda x, y: self._wn_sim.similarity(x, y, self._sim_name)
# construct similarity graphs
sim_graph = SimGraph(synsets, sim_metric)
# get pagerank scores of synsets
rank_scores = sim_graph.page_rank()
results = []
for w in words_origin:
if w in words:
candidate_scores = {s:rank_scores[s] for s in words_synsets[w]}
results.append((w, Counter(candidate_scores).most_common(1)[0][0]))
else:
results.append((w, None))
return results
