def test_predicate_consolidation(self):
"""
Test whether the predictor can correctly consolidate multiword
predicates.
"""
tokenizer = SpacyTokenizer(pos_tags=True)
sent_tokens = tokenizer.tokenize(
"In December, John decided to join the party.")
# Emulate predications - for both "decided" and "join"
predictions = [
[
"B-ARG2", "I-ARG2", "O", "B-ARG0", "B-V", "B-ARG1", "I-ARG1",
"I-ARG1", "I-ARG1", "O"
],
[
"O", "O", "O", "B-ARG0", "B-BV", "I-BV", "B-V", "B-ARG1",
"I-ARG1", "O"
],
]
# Consolidate
pred_dict = consolidate_predictions(predictions, sent_tokens)
# Check that only "decided to join" is left
assert len(pred_dict) == 1
tags = list(pred_dict.values())[0]
assert get_predicate_text(sent_tokens, tags) == "decided to join"
def test_more_than_two_overlapping_predicates(self):
"""
Test whether the predictor can correctly consolidate multiword
predicates.
"""
tokenizer = SpacyTokenizer(pos_tags=True)
sent_tokens = tokenizer.tokenize(
"John refused to consider joining the club.")
# Emulate predications - for "refused" and "consider" and "joining"
predictions = [
[
"B-ARG0", "B-V", "B-ARG1", "I-ARG1", "I-ARG1", "I-ARG1",
"I-ARG1", "O"
],
[
"B-ARG0", "B-BV", "I-BV", "B-V", "B-ARG1", "I-ARG1", "I-ARG1",
"O"
],
["B-ARG0", "B-BV", "I-BV", "I-BV", "B-V", "B-ARG1", "I-ARG1", "O"],
]
# Consolidate
pred_dict = consolidate_predictions(predictions, sent_tokens)
# Check that only "refused to consider to join" is left
assert len(pred_dict) == 1
tags = list(pred_dict.values())[0]
assert get_predicate_text(sent_tokens,
tags) == "refused to consider joining"