def test_oracle_moves_missing_B(en_vocab):
words = ["B", "52", "Bomber"]
biluo_tags = [None, None, "L-PRODUCT"]
doc = Doc(en_vocab, words=words)
example = Example.from_dict(doc, {"words": words, "entities": biluo_tags})
moves = BiluoPushDown(en_vocab.strings)
move_types = ("M", "B", "I", "L", "U", "O")
for tag in biluo_tags:
if tag is None:
continue
elif tag == "O":
moves.add_action(move_types.index("O"), "")
else:
action, label = tag.split("-")
moves.add_action(move_types.index("B"), label)
moves.add_action(move_types.index("I"), label)
moves.add_action(move_types.index("L"), label)
moves.add_action(move_types.index("U"), label)
moves.get_oracle_sequence(example)
def test_oracle_moves_whitespace(en_vocab):
words = ["production", "\n", "of", "Northrop", "\n", "Corp.", "\n", "'s", "radar"]
biluo_tags = ["O", "O", "O", "B-ORG", None, "I-ORG", "L-ORG", "O", "O"]
doc = Doc(en_vocab, words=words)
example = Example.from_dict(doc, {"entities": biluo_tags})
moves = BiluoPushDown(en_vocab.strings)
move_types = ("M", "B", "I", "L", "U", "O")
for tag in biluo_tags:
if tag is None:
continue
elif tag == "O":
moves.add_action(move_types.index("O"), "")
else:
action, label = tag.split("-")
moves.add_action(move_types.index(action), label)
moves.get_oracle_sequence(example)
def tsys(vocab, entity_types):
actions = BiluoPushDown.get_actions(entity_types=entity_types)
return BiluoPushDown(vocab.strings, actions)
def test_negative_sample_key_is_in_config(vocab, entity_types):
actions = BiluoPushDown.get_actions(entity_types=entity_types)
tsys = BiluoPushDown(vocab.strings,
actions,
incorrect_spans_key="non_entities")
assert tsys.cfg["neg_key"] == "non_entities"