def test_word_similarity():
from sematch.semantic.similarity import WordNetSimilarity
wns = WordNetSimilarity()
dog = wns.word2synset('dog')
cat = wns.word2synset('cat')
# Measuring semantic similarity between concepts using Path method
assert wns.similarity(dog[0], cat[0], 'path') is not None # 0.2
# Computing English word similarity using Li method
assert wns.word_similarity('dog', 'cat',
'li') is not None # 0.449327301063
# Computing Spanish word similarity using Lin method
assert wns.monol_word_similarity('perro', 'gato', 'spa',
'lin') is not None #0.876800984373
# Computing Chinese word similarity using Wu & Palmer method
assert wns.monol_word_similarity('狗', '猫', 'cmn',
'wup') is not None # 0.857142857143
# Computing Spanish and English word similarity using Resnik method
assert wns.crossl_word_similarity('perro', 'cat', 'spa', 'eng',
'res') is not None #7.91166650904
# Computing Spanish and Chinese word similarity using Jiang & Conrad method
assert wns.crossl_word_similarity('perro', '猫', 'spa', 'cmn',
'jcn') is not None #0.31023804699
# Computing Chinese and English word similarity using WPath method
assert wns.crossl_word_similarity('狗', 'cat', 'cmn', 'eng',
'wpath') is not None #0.593666388463
def test_wordnet_similarity():
from sematch.semantic.similarity import WordNetSimilarity
wns = WordNetSimilarity()
dog = wns.word2synset('dog')
cat = wns.word2synset('cat')
# Measuring semantic similarity between concepts using Path method
assert wns.similarity(dog[0], cat[0], 'path') is not None # 0.2
# Computing English word similarity using Li method
assert wns.word_similarity('dog', 'cat', 'li') is not None# 0.449327301063
# Computing Spanish word similarity using Lin method
assert wns.monol_word_similarity('perro', 'gato', 'spa', 'lin') is not None#0.876800984373
# Computing Chinese word similarity using Wu & Palmer method
assert wns.monol_word_similarity('狗', '猫', 'cmn', 'wup') is not None# 0.857142857143
# Computing Spanish and English word similarity using Resnik method
assert wns.crossl_word_similarity('perro', 'cat', 'spa', 'eng', 'res') is not None#7.91166650904
# Computing Spanish and Chinese word similarity using Jiang & Conrad method
assert wns.crossl_word_similarity('perro', '猫', 'spa', 'cmn', 'jcn') is not None#0.31023804699
# Computing Chinese and English word similarity using WPath method
assert wns.crossl_word_similarity('狗', 'cat', 'cmn', 'eng', 'wpath') is not None#0.593666388463
def test_wordsim_evaluation():
from sematch.evaluation import WordSimEvaluation
from sematch.semantic.similarity import WordNetSimilarity
evaluation = WordSimEvaluation()
print evaluation.dataset_names()
wns = WordNetSimilarity()
# define similarity metrics
wpath = lambda x, y: wns.word_similarity_wpath(x, y, 0.8)
# evaluate similarity metrics
print evaluation.evaluate_metric('wpath', wpath, 'noun_simlex')
# performa Steiger's Z significance Test
print evaluation.statistical_test('wpath', 'path', 'noun_simlex')
wpath_es = lambda x, y: wns.monol_word_similarity(x, y, 'spa', 'path')
wpath_en_es = lambda x, y: wns.crossl_word_similarity(
x, y, 'eng', 'spa', 'wpath')
print evaluation.evaluate_metric('wpath_es', wpath_es, 'rg65_spanish')
print evaluation.evaluate_metric('wpath_en_es', wpath_en_es, 'rg65_EN-ES')
from sematch.semantic.similarity import WordNetSimilarity
wn_sim = WordNetSimilarity()
w1 = 'gil'
lang1 = 'pol'
w2 = "sowa"
lang2 = 'pol'
result = []
# for sim_type in ['path','lch','wup','li','res','lin','jcn','wpath','zhou']:
for sim_type in ['path', 'wup', 'li', 'res', 'lin', 'jcn', 'wpath', 'zhou']:
sim = wn_sim.crossl_word_similarity(w1, w2, lang1, lang2, sim_type)
tmp = {'name': sim_type, 'sim': sim}
result.append(tmp)
print(tmp)
avg = (result[0]['sim'] + result[1]['sim'] + result[2]['sim'] +
result[3]['sim'] / 10 + result[4]['sim'] + result[5]['sim'] +
result[6]['sim']) / 7
print("average from other methods: " + str(avg))
from sematch.semantic.similarity import WordNetSimilarity
wns = WordNetSimilarity()
# Computing English word similarity using Li method
wns.word_similarity('dog', 'cat', 'li') # 0.449327301063
# Computing Spanish word similarity using Lin method
wns.monol_word_similarity('perro', 'gato', 'spa', 'lin') #0.876800984373
# Computing Chinese word similarity using Wu & Palmer method
wns.monol_word_similarity('狗', '猫', 'cmn', 'wup') # 0.857142857143
# Computing Spanish and English word similarity using Resnik method
wns.crossl_word_similarity('perro', 'cat', 'spa', 'eng', 'res') #7.91166650904
# Computing Spanish and Chinese word similarity using Jiang & Conrad method
wns.crossl_word_similarity('perro', '猫', 'spa', 'cmn', 'jcn') #0.31023804699
# Computing Chinese and English word similarity using WPath method
wns.crossl_word_similarity('狗', 'cat', 'cmn', 'eng', 'wpath') #0.593666388463