def getSentences(text):
nlp = Spanish()
nlp.add_pipe(nlp.create_pipe('sentencizer'))
document = nlp(text)
return [sent.string.strip() for sent in document.sents]
# Output the annotation file
annotation_filepath = './evaluation/NER/' + doc[:-3] + 'ann'
with open(annotation_filepath, 'w', encoding='utf-8') as annotation_file:
annotation_file.write(output)
annotation_file.close()
if __name__ == "__main__":
# load the model you trained
model = SequenceTagger.load(
'resources/taggers/medium_updated/final-model.pt')
## Create spanish sentence segmenter with Spacy
# the sentence segmentation by spacy is non-destructive, i.e., the empty lines are considered when getting a span of a given word/entity
nlp = Spanish()
sentencizer = nlp.create_pipe("sentencizer")
nlp.add_pipe(sentencizer)
test_dir = "./data/datasets/test-background-set-to-publish/"
if not os.path.exists("./evaluation/NER/"):
os.makedirs("./evaluation/NER/")
for doc in os.listdir(
test_dir
): #For each document in test_dir build the respective annotation file with predicted entities
doc_filepath = test_dir + doc
build_annotation_file(doc, doc_filepath, model)