def _get_tars_formatted_sentence(self, label, sentence):
original_text = sentence.to_tokenized_string()
label_text_pair = (f"{label} {self.separator} {original_text}"
if self.prefix else
f"{original_text} {self.separator} {label}")
label_length = 0 if not self.prefix else len(label.split(" ")) + len(
self.separator.split(" "))
# make a tars sentence where all labels are O by default
tars_sentence = Sentence(label_text_pair, use_tokenizer=False)
for entity_label in sentence.get_labels(self.label_type):
if entity_label.value == label:
new_span = [
tars_sentence.get_token(token.idx + label_length)
for token in entity_label.span
]
tars_sentence.add_complex_label(
self.static_label_type,
SpanLabel(Span(new_span), value="entity"))
return tars_sentence
def _label(self, sentence: Sentence):
"""
This will add a complex_label to the given sentence for every match.span() for every registered_mapping.
If a match span overlaps with a token span an exception is raised.
"""
collection = RegexpTagger.TokenCollection(sentence)
for label, pattern in self._regexp_mapping.items():
for match in pattern.finditer(sentence.to_original_text()):
span: Tuple[int, int] = match.span()
try:
token_span = collection.get_token_span(span)
except ValueError:
raise Exception(
f"The match span {span} for label '{label}' is overlapping with a token!"
)
sentence.add_complex_label(label, SpanLabel(token_span, label))
