def write_sentence_documents(sentences: List[str],
labels: List[str],
path: Path,
labeled=True):
typesystem = TypeSystem()
cas = Cas(typesystem=typesystem)
SentenceType = typesystem.create_type(
"de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.Sentence")
SentimentType = typesystem.create_type("webanno.custom.Sentiment")
typesystem.add_feature(type_=SentimentType,
name="value",
rangeTypeName="uima.cas.String")
cas.sofa_string = " ".join(sentences)
begin = 0
for sentence, label in zip(sentences, labels):
end = begin + len(sentence)
cas_sentence = SentenceType(begin=begin, end=end)
sentiment_annotation = SentimentType(begin=begin, end=end, value=label)
begin = end + 1
cas.add_annotation(cas_sentence)
if labeled:
cas.add_annotation(sentiment_annotation)
cas.to_xmi(path, pretty_print=True)
for sentence in cas.select(SENTENCE_TYPE):
print(cas.get_covered_text(sentence))
def predict(self, cas: Cas, layer: str, feature: str, project_id: str,
document_id: str, user_id: str):
# Extract the tokens from the CAS and create a spacy doc from it
cas_tokens = cas.select(TOKEN_TYPE)
words = [cas.get_covered_text(cas_token) for cas_token in cas_tokens]
doc = Doc(self._model.vocab, words=words)
# Find the named entities
self._model.get_pipe("ner")(doc)
# For every entity returned by spacy, create an annotation in the CAS
for named_entity in doc.ents:
begin = cas_tokens[named_entity.start].begin
end = cas_tokens[named_entity.end - 1].end
label = named_entity.label_
prediction = create_prediction(cas, layer, feature, begin, end,
label)
cas.add_annotation(prediction)
def predict(self, cas: Cas, layer: str, feature: str, project_id: str,
document_id: str, user_id: str):
# Extract the tokens from the CAS and create a spacy doc from it
words = [
cas.get_covered_text(cas_token)
for cas_token in self.iter_tokens(cas)
]
doc = Doc(self._model.vocab, words=words)
# Find the named entities
self._model.tagger(doc)
# For every token, extract the POS tag and create an annotation in the CAS
for cas_token, spacy_token in zip(self.iter_tokens(cas), doc):
prediction = self.create_prediction(cas, layer, feature,
cas_token.begin, cas_token.end,
spacy_token.pos_)
cas.add_annotation(prediction)
def predict(self, cas: Cas, layer: str, feature: str, project_id: str,
document_id: str, user_id: str):
# Extract the tokens from the CAS and create a spacy doc from it
words = [
cas.get_covered_text(cas_token)
for cas_token in cas.select(TOKEN_TYPE)
]
doc = Doc(self._model.vocab, words=words)
# Get the pos tags
self._model.get_pipe("tok2vec")(doc)
self._model.get_pipe("tagger")(doc)
# For every token, extract the POS tag and create an annotation in the CAS
for cas_token, spacy_token in zip(cas.select(TOKEN_TYPE), doc):
prediction = create_prediction(cas, layer, feature,
cas_token.begin, cas_token.end,
spacy_token.tag_)
cas.add_annotation(prediction)