AcroBERT / popularity.py
Lihuchen's picture
initial
fa0a93c
raw
history blame
987 Bytes
import utils
import spacy
from maddog import Extractor
import constant
# load
nlp = spacy.load("en_core_web_sm")
ruleExtractor = Extractor()
kb = utils.load_acronym_kb('../input/acronym_kb.json')
def popularity(sentence):
tokens = [t.text for t in nlp(sentence) if len(t.text.strip()) > 0]
rulebased_pairs = ruleExtractor.extract(tokens, constant.RULES)
results = list()
for acronym in rulebased_pairs.keys():
if rulebased_pairs[acronym][0] != '':
results.append((acronym, rulebased_pairs[acronym][0]))
else:
pred = utils.get_candidate(kb, acronym, can_num=1)
results.append((acronym, pred[0]))
return results
if __name__ == '__main__':
sentence = \
"NCBI This new genome assembly and the annotation are tagged as a RefSeq genome by NCBI and thus provide substantially enhanced genomic resources for future research involving S. scovelli."
results = run_eval(sentence=sentence)
print(results)