def test_wordnet(self):
self.assertIsInstance(wordnet.langs(), list)
self.assertIn("tha", wordnet.langs())
self.assertEqual(
wordnet.synset("spy.n.01").lemma_names("tha"), ["สปาย", "สายลับ"])
self.assertIsNotNone(wordnet.synsets("นก"))
self.assertIsNotNone(wordnet.all_synsets(pos=wn.ADJ))
self.assertIsNotNone(wordnet.lemmas("นก"))
self.assertIsNotNone(wordnet.all_lemma_names(pos=wn.ADV))
self.assertIsNotNone(wordnet.lemma("cat.n.01.cat"))
self.assertEqual(wordnet.morphy("dogs"), "dog")
bird = wordnet.synset("bird.n.01")
mouse = wordnet.synset("mouse.n.01")
self.assertEqual(wordnet.path_similarity(bird, mouse),
bird.path_similarity(mouse))
self.assertEqual(wordnet.wup_similarity(bird, mouse),
bird.wup_similarity(mouse))
self.assertEqual(wordnet.lch_similarity(bird, mouse),
bird.lch_similarity(mouse))
cat_key = wordnet.synsets("แมว")[0].lemmas()[0].key()
self.assertIsNotNone(wordnet.lemma_from_key(cat_key))
def test_wordnet(self):
self.assertIsNotNone(wordnet.langs())
self.assertEqual(
wordnet.synset("spy.n.01").lemma_names("tha"), ["สปาย", "สายลับ"]
)
self.assertIsNotNone(wordnet.synsets("นก"))
self.assertIsNotNone(wordnet.all_synsets(pos=wn.ADJ))
self.assertIsNotNone(wordnet.lemmas("นก"))
self.assertIsNotNone(wordnet.all_lemma_names(pos=wn.ADV))
self.assertIsNotNone(wordnet.lemma("cat.n.01.cat"))
self.assertEqual(wordnet.morphy("dogs"), "dog")
bird = wordnet.synset("bird.n.01")
mouse = wordnet.synset("mouse.n.01")
self.assertEqual(
wordnet.path_similarity(bird, mouse), bird.path_similarity(mouse)
)
self.assertEqual(
wordnet.wup_similarity(bird, mouse), bird.wup_similarity(mouse)
)
cat_key = wordnet.synsets("แมว")[0].lemmas()[0].key()
self.assertIsNotNone(wordnet.lemma_from_key(cat_key))
def compute_wordnet_path_scores(pairs):
"""
Compute WordNet path similarity for a list of input word pairs
Note: Thai WordNet has 3 methods to compute a similarity value: wordnet.path_similarity, wordnet.lch_similarity, wordnet.wup_similarity
lch_similarity we can't use. path_similarity seems to have better results than wup_similarity
If we don't find a path between the two works, we add "None" to the result list
@returns: this list of simility scores, and the number of OOV-word-pairs
"""
structed_oov_pairs = 0
wn_scores = []
for index, pair in enumerate(pairs):
w1 = wordnet.synsets(pair[0])
w2 = wordnet.synsets(pair[1])
if len(w1) > 0 and len(w2) > 0:
# just use the first synset of each term
if WORDNET_PATH_SIMILARITY_TYPE == 'first_synset':
path = wordnet.path_similarity(w1[0], w2[0])
# return the highest sim between all synset combinations
elif WORDNET_PATH_SIMILARITY_TYPE == 'most_similar':
path = -1
for syn1 in w1:
for syn2 in w2:
tmppath = wordnet.path_similarity(syn1, syn2)
if tmppath and tmppath > path: path = tmppath
if path == -1:
# if no path found, set back to None
path = None
else:
raise RuntimeError(
'WORDNET_PATH_SIMILARITY_TYPE is not set in config!')
wn_scores.append(path)
else:
wn_scores.append(None)
structed_oov_pairs += 1
return wn_scores, structed_oov_pairs
def compute_wordnet_path_scores(pairs):
"""
Compute WordNet path similarity for a list of input word pairs
Note: Thai WordNet has 3 methods to compute a similarity value: wordnet.path_similarity, wordnet.lch_similarity, wordnet.wup_similarity
lch_similarity we can't use. path_similarity seems to have better results than wup_similarity
If we don't find a path between the two works, we add "None" to the result list
@returns: this list of simility scores, and the number of OOV-word-pairs
"""
print("DEBUG: starting compute_wordnet_path_scores")
from pythainlp.corpus import wordnet
structed_oov_pairs = 0 # wohlg: we count word pairs for which we have no path
wn_scores = []
for index, pair in enumerate(pairs):
w1 = wordnet.synsets(pair[0])
w2 = wordnet.synsets(pair[1])
if len(w1) > 0 and len(w2) > 0:
if WORDNET_PATH_SIMILARITY_TYPE == 'first_synset': # just use the first synset of each term
path = wordnet.path_similarity(w1[0], w2[0])
# path = wordnet.lch_similarity(w1[0], w2[0]) ## we can't use it, requires the same part-of-speech for both words
# path = wordnet.wup_similarity(w1[0], w2[0])
elif WORDNET_PATH_SIMILARITY_TYPE == 'most_similar': # return the highest sim between all synset combinations
path = -1
for syn1 in w1:
for syn2 in w2:
tmppath = wordnet.path_similarity(syn1, syn2)
if tmppath and tmppath > path: path = tmppath
if path == -1:
path = None # if no path found, set back to None
wn_scores.append(path)
else:
wn_scores.append(None)
structed_oov_pairs += 1
return wn_scores, structed_oov_pairs