count = cos(v, self.model.wv[ps])
best_syn = ps
try:
if ps.capitalize() in self.model.vocab:
cap = ps.capitalize()
if count <= cos(v, self.model.wv[cap].capitalize()):
count = cos(v, self.model.wv[cap].capitalize())
best_syn = ps
except:
#print(f"{ps} not in vocab")
pass
return best_syn
if __name__ == "__main__":
# At submission time, this program should run your best predictor (part 6).
W2VMODEL_FILENAME = 'GoogleNews-vectors-negative300.bin.gz'
predictor = Word2VecSubst(W2VMODEL_FILENAME)
for context in read_lexsub_xml(sys.argv[1]):
#print(context) # useful for debugging
#prediction = wn_simple_lesk_predictor(context)
#print(prediction)
#prediction = wn_simple_lesk_predictor(context)
prediction = predictor.improved_predictor(context)
print("{}.{} {} :: {}".format(context.lemma, context.pos, context.cid,
prediction))
def __init__(self, filename, maxlen=80):
self.tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
self.maxlen = maxlen
self.file = [i for i in read_lexsub_xml(filename)]