def ee(model, data):
e = Embedder(model)
sentences = cd.read_col_data(data)
sids, sents = zip(*[(sent.id, [t.form for t in sent])
for sent in sentences])
print("Embedding...")
elmos = e.sents2elmo(sents)
return elmos, sids
def create_weight_matrix_elmo(word2idx, n_words, vector_dimension=1024):
elmoEmbedder = Embedder('./elmo')
notFound = 0
embedding_matrix = np.zeros((n_words + 1, vector_dimension))
for word, i in word2idx.items():
sent = [[word]]
embedding_vector = elmoEmbedder.sents2elmo(sent)
embedding_vector = embedding_vector[0][0]
#print(word)
#print(i)
if (embedding_vector is not None):
embedding_matrix[i] = embedding_vector
else:
notFound = notFound + 1
#print('%s words could not found.' % notFound)
return embedding_matrix
#TODO support batches
import sys
import os
sys.path.append('.')
from ELMoForManyLangs.elmoformanylangs import Embedder
if len(sys.argv) < 3:
print('please provide embeddings and conl file')
exit(0)
converter = Embedder(sys.argv[1])
curSent = []
outFile = open(sys.argv[2] + '.elmo', 'w')
for line in open(sys.argv[2]):
if len(line) < 2:
sent = [[x[0] for x in curSent]]
emb = converter.sents2elmo(sent)[0]
for itemIdx in range(len(curSent)):
embStr = 'emb=' + ','.join([str(x) for x in emb[itemIdx]])
outFile.write('\t'.join(curSent[itemIdx] + [embStr]) + '\n')
outFile.write('\n')
curSent = []
else:
tok = line.strip().split('\t')
curSent.append(tok)
outFile.close()