def is_corruption_shuffled(entry):
a = entry['sentence_A']
b = entry['sentence_B']
if sorted(a.split()) == sorted(b.split()):
norm_o = norm(entry['sentence_A_original'])
if edit_distance(norm_o, norm(a)) > edit_distance(norm_o, norm(b)):
return 1
else:
return 2
return 0
def are_sem_opposites(entry):
a = entry['sentence_A']
b = entry['sentence_B']
# Are near synonyms but not qualifier replacement
if one_word_diff(entry['sentence_A'], entry['sentence_B']):
# S1S3 same set pairs only have a 0.9% chance of being labeled entailment
if entry['entailment_label'] != 'ENTAILMENT' and not is_corruption_det_replace(entry):
norm_o = norm(entry['sentence_A_original'])
if edit_distance(norm_o, norm(a)) > edit_distance(norm_o, norm(b)):
return 1
else:
return 2
return 0
def is_corruption_det_replace(entry):
def normalize(sent):
s = sent.lower().split()
s = [ w for w in s if (w!='a' and w!='the') ]
return s
a = entry['sentence_A']
b = entry['sentence_B']
if normalize(a) == normalize(b):
norm_o = norm(entry['sentence_A_original'])
if edit_distance(norm_o, norm(a)) > edit_distance(norm_o, norm(b)):
return 1
else:
return 2
return 0
def closest_match(sent, dataset):
"""
Using edit distance, find the closest key match to the given sentence.
"""
min_dist = float('inf')
match = None
if dataset == 'FLICKR':
data_reverse = flickr_reverse
elif dataset == 'SEMEVAL':
data_reverse = msr_reverse
else:
raise Exception('unknown dataset %s' % dataset)
# take what you can get
if sent in data_reverse:
return sent
bins = defaultdict(list)
for s in data_reverse.keys():
# Token-based edit distance
dist = edit_distance(sent.split(), s.split())
bins[dist].append(s)
lowest = min(bins.keys())
for s in bins[lowest]:
dist = edit_distance(sent, s)
# guaranteed okay
if dist == 0:
return s
if dist < min_dist:
min_dist = dist
match = s
assert match != None, 'no match found for %s' % sent
return match
def closest_match(sent, dataset):
"""
Using edit distance, find the closest key match to the given sentence.
"""
min_dist = float('inf')
match = None
if dataset == 'FLICKR':
data_reverse = flickr_reverse
elif dataset == 'SEMEVAL':
data_reverse = msr_reverse
else:
raise Exception('unknown dataset %s' % dataset)
# take what you can get
if sent in data_reverse:
return sent
bins = defaultdict(list)
for s in data_reverse.keys():
# Token-based edit distance
dist = edit_distance(sent.split(), s.split())
bins[dist].append(s)
lowest = min(bins.keys())
for s in bins[lowest]:
dist = edit_distance(sent, s)
# guaranteed okay
if dist == 0:
return s
if dist < min_dist:
min_dist = dist
match = s
assert match != None, 'no match found for %s' % sent
return match
