def __init__(self, path, load_ext_feats=False):
"""
Create a Castor dataset involving pairs of texts
"""
fields = [('id', self.ID_FIELD), ('sentence_1', self.TEXT_FIELD), ('sentence_2', self.TEXT_FIELD),
('ext_feats', self.EXT_FEATS_FIELD), ('label', self.LABEL_FIELD),
('aid', self.AID_FIELD), ('sentence_1_raw', self.RAW_TEXT_FIELD), ('sentence_2_raw', self.RAW_TEXT_FIELD)]
examples = []
with open(os.path.join(path, 'a.toks'), 'r') as f1, open(os.path.join(path, 'b.toks'), 'r') as f2:
sent_list_1 = [l.rstrip('.\n').split(' ') for l in f1]
sent_list_2 = [l.rstrip('.\n').split(' ') for l in f2]
word_to_doc_cnt = get_pairwise_word_to_doc_freq(sent_list_1, sent_list_2)
self.word_to_doc_cnt = word_to_doc_cnt
if not load_ext_feats:
overlap_feats = get_pairwise_overlap_features(sent_list_1, sent_list_2, word_to_doc_cnt)
else:
overlap_feats = np.loadtxt(os.path.join(path, 'overlap_feats.txt'))
with open(os.path.join(path, 'id.txt'), 'r') as id_file, open(os.path.join(path, 'sim.txt'), 'r') as label_file:
for i, (pair_id, l1, l2, ext_feats, label) in enumerate(zip(id_file, sent_list_1, sent_list_2, overlap_feats, label_file)):
pair_id = pair_id.rstrip('.\n')
label = label.rstrip('.\n')
example_list = [pair_id, l1, l2, ext_feats, label, i + 1, ' '.join(l1), ' '.join(l2)]
example = Example.fromlist(example_list, fields)
examples.append(example)
super(CastorPairDataset, self).__init__(examples, fields)
def __init__(self, path):
"""
Create a MSRP dataset instance
"""
fields = [('id', self.ID_FIELD), ('sentence_1', self.TEXT_FIELD), ('sentence_2', self.TEXT_FIELD), ('ext_feats', self.EXT_FEATS_FIELD),
('label', self.LABEL_FIELD), ('sentence_1_raw', self.RAW_TEXT_FIELD), ('sentence_2_raw', self.RAW_TEXT_FIELD)]
examples = []
with open(os.path.join(path, 'a.toks'), 'r') as f1, open(os.path.join(path, 'b.toks'), 'r') as f2:
sent_list_1 = [l.rstrip('.\n').split(' ') for l in f1]
sent_list_2 = [l.rstrip('.\n').split(' ') for l in f2]
word_to_doc_cnt = get_pairwise_word_to_doc_freq(sent_list_1, sent_list_2)
self.word_to_doc_cnt = word_to_doc_cnt
with open(os.path.join(path, 'id.txt'), 'r') as id_file, open(os.path.join(path, 'sim.txt'), 'r') as label_file:
for pair_id, l1, l2, label in zip(id_file, sent_list_1, sent_list_2, label_file):
pair_id = pair_id.rstrip('.\n')
label = label.rstrip('.\n')
ext_feats = []
# Number features
sent1_nums, sent2_nums = [], []
match = self.NUMBER_PATTERN.search(' '.join(l1))
if match:
for g in match.groups():
if g is not None:
sent1_nums.append(g)
match = self.NUMBER_PATTERN.search(' '.join(l2))
if match:
for g in match.groups():
if g is not None:
sent2_nums.append(g)
sent1_nums = set(sent1_nums)
sent2_nums = set(sent2_nums)
exact = int(sent1_nums == sent2_nums)
superset = int(sent1_nums.issuperset(sent2_nums) or sent2_nums.issuperset(sent1_nums))
ext_feats.append(1 if (exact or (len(sent1_nums) == 0 and len(sent2_nums) == 0)) else 0)
ext_feats.append(exact)
ext_feats.append(superset)
# Length difference
ext_feats.append(len(l2) - len(l1))
# Overlap
overlap = len(set(l1) & set(l2))
ext_feats.append(overlap / len(l1))
ext_feats.append(overlap / len(l2))
example = Example.fromlist([pair_id, l1, l2, ext_feats, label, ' '.join(l1), ' '.join(l2)], fields)
examples.append(example)
super(MSRP, self).__init__(examples, fields)
def __init__(self, path):
"""
Create a Castor dataset involving pairs of texts
"""
fields = [('id', self.ID_FIELD), ('sentence_1', self.TEXT_FIELD),
('sentence_2', self.TEXT_FIELD),
('ext_feats', self.EXT_FEATS_FIELD),
('label', self.LABEL_FIELD),
('sentence_1_raw', self.RAW_TEXT_FIELD),
('sentence_2_raw', self.RAW_TEXT_FIELD)]
examples = []
ids, labels, sent_list_1, sent_list_2 = [], [], [], []
with open(path) as f:
for line in f:
content = json.loads(line)
sent_list_1.append(content['question'])
sent_list_2.append(content['qaquestion'])
word_to_doc_cnt = get_pairwise_word_to_doc_freq(
sent_list_1, sent_list_2)
overlap_feats = get_pairwise_overlap_features(sent_list_1, sent_list_2,
word_to_doc_cnt)
self.word_to_doc_cnt = word_to_doc_cnt
with open(path) as f:
for line in f:
content = json.loads(line)
ids.append(content['qid'])
labels.append(content['qarel'])
for pair_id, l1, l2, ext_feats, label in zip(ids, sent_list_1,
sent_list_2,
overlap_feats, labels):
example = Example.fromlist([
pair_id, l1, l2, ext_feats, label, ' '.join(l1), ' '.join(l2)
], fields)
examples.append(example)
super(SemevalDataset, self).__init__(examples, fields)
def __init__(self, path, **kwargs):
"""
Create a Semeval dataset instance
"""
fields = [('qid', self.QID_FIELD), ('qaid', self.QID_FIELD),
('label', self.LABEL_FIELD), ('sentence_1', self.TEXT_FIELD),
('sentence_2', self.TEXT_FIELD),
('sentence_1_raw', self.RAW_TEXT_FIELD),
('sentence_2_raw', self.RAW_TEXT_FIELD),
('ext_feats', self.EXT_FEATS_FIELD)]
examples = []
with open(path) as infile:
for line in infile:
content = json.loads(line)
sent_list_1 = content['question']
sent_list_2 = content['qaquestion']
word_to_doc_cnt = get_pairwise_word_to_doc_freq(
sent_list_1, sent_list_2)
overlap_feats = get_pairwise_overlap_features(
sent_list_1, sent_list_2, word_to_doc_cnt)
overlap_feats = []
values = [
content['qid'], content['qaid'], content['qarel'],
content['question'], content['qaquestion'],
' '.join(content['question']),
' '.join(content['qaquestion']), overlap_feats
]
examples.append(Example.fromlist(values, fields))
super(Semeval, self).__init__(examples, fields, **kwargs)
