def __init__(self, epochs=10, eta=.0001):
self.decoder = ViterbiDecompounder()
self.parameters_for_epoch = []
self.n_epochs = epochs
self.eta = eta
self.n_features = ViterbiDecompounder.n_features
modelSetup,
nAccuracy=args.nAccuracy,
globalNN=args.globalNN,
similarityThreshold=args.similarityThreshold,
prototype_file=args.prototypeFile)
if args.mode == "lattices":
for line in sys.stdin:
print(
base_decompounder.get_decompound_lattice(
line.decode('utf8').rstrip('\n').title(), ))
elif args.mode == "w2v_dict":
for word in base_decompounder.model.vocab.keys():
print word.encode('utf-8')
elif args.mode in ["1-best", "dict_w2v"]:
vit = ViterbiDecompounder()
vit.load_weights(modelSetup["WEIGHTS"])
words = []
if args.mode == "1-best":
words = map(lambda line: line.decode('utf8').strip(), sys.stdin)
else:
words = base_decompounder.model.vocab.keys()
print >> sys.stderr, "# words: %d" % len(words)
def process_word(word):
lattice = Lattice(base_decompounder.get_decompound_lattice(word))
viterbi_path = vit.viterbi_decode(Compound(word, None, lattice))
return [
word.encode('utf-8'),
