def LF_complement_left_row(c):
return (-1 if (overlap(
["complement", "complementary"],
chain.from_iterable(
[get_row_ngrams(c.part),
get_left_ngrams(c.part, window=10)]),
)) else 0)
def get_word_feats(span):
attrib = "words"
if span.stable_id not in unary_word_feats:
unary_word_feats[span.stable_id] = set()
for ngram in tokens_to_ngrams(span.get_attrib_tokens(attrib),
n_min=1,
n_max=2):
feature = f"CONTAINS_{attrib.upper()}_[{ngram}]"
unary_word_feats.add(feature)
for ngram in get_left_ngrams(
span,
window=settings["featurization"]["content"]["word_feature"]
["window"],
n_max=2,
attrib=attrib,
):
feature = f"LEFT_{attrib.upper()}_[{ngram}]"
unary_word_feats.add(feature)
for ngram in get_right_ngrams(
span,
window=settings["featurization"]["content"]["word_feature"]
["window"],
n_max=2,
attrib=attrib,
):
feature = f"RIGHT_{attrib.upper()}_[{ngram}]"
unary_word_feats.add(feature)
for f in unary_word_feats[span.stable_id]:
yield f
def LF_negative_number_left(c):
return (
TRUE
if any(
[re.match(r"-\s*\d+", ngram) for ngram in get_left_ngrams(c.temp, window=4)]
)
else ABSTAIN
)
def LF_complement_left_row(c):
"""Return False if temp mention's ngrams align with the following keywords."""
return (FALSE if (overlap(
["complement", "complementary"],
chain.from_iterable(
[get_row_ngrams(c.part),
get_left_ngrams(c.part, window=10)]),
)) else ABSTAIN)
def _get_word_feats(span: SpanMention) -> Iterator[str]:
attrib = "words"
if span.stable_id not in unary_word_feats:
unary_word_feats[span.stable_id] = set()
for ngram in tokens_to_ngrams(span.get_attrib_tokens(attrib),
n_min=1,
n_max=2):
feature = f"CONTAINS_{attrib.upper()}_[{ngram}]"
unary_word_feats[span.stable_id].add(feature)
for ngram in get_left_ngrams(
span,
window=settings["featurization"]["textual"]["word_feature"]
["window"],
n_max=2,
attrib=attrib,
):
feature = f"LEFT_{attrib.upper()}_[{ngram}]"
unary_word_feats[span.stable_id].add(feature)
for ngram in get_right_ngrams(
span,
window=settings["featurization"]["textual"]["word_feature"]
["window"],
n_max=2,
attrib=attrib,
):
feature = f"RIGHT_{attrib.upper()}_[{ngram}]"
unary_word_feats[span.stable_id].add(feature)
unary_word_feats[span.stable_id].add((
f"SPAN_TYPE_["
f"{'IMPLICIT' if isinstance(span, ImplicitSpanMention) else 'EXPLICIT'}"
f"]"))
if span.get_span()[0].isupper():
unary_word_feats[span.stable_id].add("STARTS_WITH_CAPITAL")
unary_word_feats[span.stable_id].add(f"LENGTH_{span.get_num_words()}")
for f in unary_word_feats[span.stable_id]:
yield f
def LF_to_left(c):
return 1 if "to" in get_left_ngrams(c.temp, window=2) else 0
def LF_to_left(c):
return TRUE if "to" in get_left_ngrams(c[1], window=2) else ABSTAIN
def LF_negative_number_left(c):
"""Return True if temp mention's left ngrams contain negative number."""
return (TRUE if any([
re.match(r"-\s*\d+", ngram)
for ngram in get_left_ngrams(c.temp, window=4)
]) else ABSTAIN)
def LF_to_left(c):
"""Return True if temp mention's left ngrams contain ``to''."""
return TRUE if "to" in get_left_ngrams(c.temp, window=2) else ABSTAIN
