def test_multiprocess_type_data(self):
"""ENTITY SYMBOLS
{
"multi word alias2":[["Q2",5.0],["Q1",3.0],["Q4",2.0]],
"alias1":[["Q1",10.0],["Q4",6.0]],
"alias3":[["Q1",30.0]],
"alias4":[["Q4",20.0],["Q3",15.0],["Q2",1.0]]
}
TYPE LABELS
{
"Q1": [0, 1],
"Q2": [2],
"Q3": [],
"Q4": [1]
}
"""
max_seq_len = 7
max_aliases = 4
self.args.data_config.max_aliases = max_aliases
self.args.data_config.max_seq_len = max_seq_len
input_data = [
{
"aliases": ["alias1", "multi word alias2"],
"qids": ["Q1", "Q4"],
"sent_idx_unq": 0,
"sentence": "alias1 or multi word alias2",
"spans": [[0, 1], [2, 5]],
"gold": [True, True],
},
{
"aliases": ["alias1", "multi word alias2"],
"qids": ["Q1", "Q4"],
"sent_idx_unq": 1,
"sentence": "alias1 or multi word alias2",
"spans": [[0, 1], [2, 5]],
"gold": [True, True],
},
]
Y_dict = {
"gold_type_id":
torch.tensor([[0 + 1, 1 + 1, -1, -1], [0 + 1, 1 + 1, -1, -1]]),
}
utils.write_jsonl(self.temp_file_name, input_data)
use_weak_label = True
dataset = BootlegDataset(
self.args,
name="Bootleg_test",
dataset=self.temp_file_name,
use_weak_label=use_weak_label,
tokenizer=self.tokenizer,
entity_symbols=self.entity_symbols,
dataset_threads=2,
split="train",
is_bert=True,
)
# As the gold is the same for all, the order won't matter
assert torch.equal(Y_dict["gold_type_id"],
dataset.Y_dict["gold_type_id"])
def test_subsent_data(self):
"""ENTITY SYMBOLS
{
"multi word alias2":[["Q2",5.0],["Q1",3.0],["Q4",2.0]],
"alias1":[["Q1",10.0],["Q4",6.0]],
"alias3":[["Q1",30.0]],
"alias4":[["Q4",20.0],["Q3",15.0],["Q2",1.0]]
}
TYPE LABELS
{
"Q1": [0, 1],
"Q2": [2],
"Q3": [],
"Q4": [1]
}
"""
# Test 1: the sentence is long and has far apart aliases so it gets split up into two subsentences;
# the types should follow
max_seq_len = 7
max_aliases = 4
self.args.data_config.max_aliases = max_aliases
self.args.data_config.max_seq_len = max_seq_len
input_data = [{
"aliases": ["alias3", "alias4"],
"qids": ["Q1", "Q2"],
"sent_idx_unq": 0,
"sentence": "alias3 cat cat cat cat cat cat alias4",
"spans": [[0, 1], [7, 8]],
"gold": [True, True],
}]
Y_dict = {
"gold_type_id":
torch.tensor([[0 + 1, -1, -1, -1], [2 + 1, -1, -1, -1]]),
}
utils.write_jsonl(self.temp_file_name, input_data)
use_weak_label = True
dataset = BootlegDataset(
self.args,
name="Bootleg_test",
dataset=self.temp_file_name,
use_weak_label=use_weak_label,
tokenizer=self.tokenizer,
entity_symbols=self.entity_symbols,
dataset_threads=1,
split="train",
is_bert=True,
)
assert torch.equal(Y_dict["gold_type_id"],
dataset.Y_dict["gold_type_id"])
def test_masked_aliases(self):
"""ENTITY SYMBOLS
{
"multi word alias2":[["Q2",5.0],["Q1",3.0],["Q4",2.0]],
"alias1":[["Q1",10.0],["Q4",6.0]],
"alias3":[["Q1",30.0]],
"alias4":[["Q4",20.0],["Q3",15.0],["Q2",1.0]]
}
TYPE LABELS
{
"Q1": [0, 1],
"Q2": [2],
"Q3": [],
"Q4": [1]
}
"""
# Test 1: this sentence gets split into two with two aliases each
# (the first alias of second split masked out). The types should follow this trend. Since split is train,
# they also ignore the gold.
max_seq_len = 7
max_aliases = 2
self.args.data_config.max_aliases = max_aliases
self.args.data_config.max_seq_len = max_seq_len
input_data = [{
"aliases": ["alias3", "alias4", "alias3"],
"qids": ["Q1", "Q4", "Q1"],
"sent_idx_unq": 0,
"sentence": "alias3 alias4 alias3",
"spans": [[0, 1], [1, 2], [2, 3]],
"gold": [True, False, False],
}]
Y_dict = {
"gold_type_id": torch.tensor([[0 + 1, 1 + 1], [-1, 0 + 1]]),
}
utils.write_jsonl(self.temp_file_name, input_data)
use_weak_label = True
dataset = BootlegDataset(
self.args,
name="Bootleg_test",
dataset=self.temp_file_name,
use_weak_label=use_weak_label,
tokenizer=self.tokenizer,
entity_symbols=self.entity_symbols,
dataset_threads=1,
split="train",
is_bert=True,
)
assert torch.equal(Y_dict["gold_type_id"],
dataset.Y_dict["gold_type_id"])
# Test 2: with the split of "dev", the subsentences should remain unchanged but the
# true index in Y_dict should be -1
max_seq_len = 7
max_aliases = 2
split = "dev"
self.args.data_config.max_aliases = max_aliases
self.args.data_config.max_seq_len = max_seq_len
input_data = [{
"aliases": ["alias3", "alias4", "alias3"],
"qids": ["Q1", "Q4", "Q1"],
"sent_idx_unq": 0,
"sentence": "alias3 alias4 alias3",
"spans": [[0, 1], [1, 2], [2, 3]],
"gold": [True, False, False],
}]
Y_dict = {
"gold_type_id": torch.tensor([[0 + 1, -1], [-1, -1]]),
}
utils.write_jsonl(self.temp_file_name, input_data)
use_weak_label = True
dataset = BootlegDataset(
self.args,
name="Bootleg_test",
dataset=self.temp_file_name,
use_weak_label=use_weak_label,
tokenizer=self.tokenizer,
entity_symbols=self.entity_symbols,
dataset_threads=1,
split=split,
is_bert=True,
)
assert torch.equal(Y_dict["gold_type_id"],
dataset.Y_dict["gold_type_id"])