all_vocab = set()
for ind, dataset in enumerate(datasets):
all_vocab = set().union(*[all_vocab, data[ind].vocabulary])
w2v = NormEmbeddingFeature.from_file(config.wordvecs,
max_rank=config.max_vocab_size,
vocabulary=all_vocab,
name='words')
features = [w2v]
if config.word_features:
features.append(SennaCapsFeature('caps'))
for ind, dataset in enumerate(datasets):
data[ind].tokens.add_features(features)
data[ind].tokens.add_inputs(windowed_inputs(config.window_size, features))
# Log word vector feature stat summary
info('{}: {}'.format(config.wordvecs, w2v.summary()))
inputs, embeddings = inputs_and_embeddings(features, config)
# Combine and reshape for convolution
seq = concat(embeddings)
cshape = (config.window_size, sum(f.output_dim for f in features))
seq = Reshape((1,) + cshape)(seq)
# Convolutions
conv_outputs = []
for filter_size, filter_num in zip(config.filter_sizes, config.filter_nums):
conv = Convolution2D(filter_num, filter_size, cshape[1],activation='relu')(seq)
config = cli_settings(['datadir', 'wordvecs'], Defaults)
data = conlldata.load_dir(config.datadir, config)
vmapper = viterbi.get_prediction_mapper(data.train.sentences, config)
w2v = NormEmbeddingFeature.from_file(config.wordvecs,
max_rank=config.max_vocab_size,
vocabulary=data.vocabulary,
name='words')
features = [w2v]
if config.word_features:
features.append(SennaCapsFeature(name='caps'))
data.tokens.add_features(features)
data.tokens.add_inputs(windowed_inputs(config.window_size, features))
# Log word vector feature stat summary
info('{}: {}'.format(config.wordvecs, w2v.summary()))
inputs, embeddings = inputs_and_embeddings(features, config)
seq = concat(embeddings)
seq = Flatten()(seq)
for size in config.hidden_sizes:
seq = Dense(size, activation=config.hidden_activation)(seq)
seq = Dropout(config.output_drop_prob)(seq)
out = Dense(data.tokens.target_dim, activation='softmax')(seq)
model = Model(input=inputs, output=out)
optimizer = get_optimizer(config)