different filter size for word embeddings

## from github discuss
ngram_filters = [3, 4, 5, 6, 7, 8]
conv_filters = []

for n_gram in ngram_filters:
    conv_filters.append(Sequential())
    conv_filters[-1].add(Convolution2D(nb_feature_maps, 1, n_gram, wv_sz))
    conv_filters[-1].add(MaxPooling2D(poolsize=(nb_tokens - n_gram + 1, 1)))
    conv_filters[-1].add(Flatten())

model = Sequential()
model.add(Merge(conv_filters, mode='concat'))
model.add(Dropout(0.5))
model.add(Dense(nb_feature_maps * len(ngram_filters), 1))
model.add(Activation('sigmoid'))