CODEWITHSUNDEEP
neural-networkkeraslstmrecurrent-neural-network
Juliano Oliveira
Juliano Oliveira

Reputation: 928

LSTM neural network with two sources of data

I have the following configuration: One lstm network that receives a text with n-grams with size 2. Below a simple schematic:

enter image description here

After some tests, I noticed that for some classes I have an significant incrise on accuracy when I use ngrams with size 3. Now I want to train a new LSTM neural network with both ngram sizes at same time, like the following schematic:

enter image description here

How can I provide the data and build this model, using keras to perform this task?

Upvotes: 0

Views: 202

Answers (1)

KrisR89
KrisR89

Reputation: 1541

I assume you already have a function to split words into n-grams, as you already have the 2-grams and 3-grams model working? Therefor I just construct a one-sample example of the word "cool" for a working example. I had to use embedding for my example, as an LSTM layer with 26^3=17576 nodes was a little too much for my computer to handle. I expect you did the same in your 3-grams code?

Below is a complete working example:

from tensorflow.keras.layers import Input, Embedding, LSTM, Dense, concatenate
from tensorflow.keras.models import Model
import numpy as np

# c->2 o->14 o->14 l->11
np_2_gram_in = np.array([[26*2+14,26*14+14,26*14+11]])#co,oo,ol
np_3_gram_in = np.array([[26**2*2+26*14+14,26**2*14+26*14+26*11]])#coo,ool

np_output = np.array([[1]])

output_shape=1
lstm_2_gram_embedding = 128
lstm_3_gram_embedding = 192

inputs_2_gram = Input(shape=(None,))
em_input_2_gram = Embedding(output_dim=lstm_2_gram_embedding, input_dim=26**2)(inputs_2_gram)
lstm_2_gram = LSTM(lstm_2_gram_embedding)(em_input_2_gram)
inputs_3_gram = Input(shape=(None,))
em_input_3_gram = Embedding(output_dim=lstm_3_gram_embedding, input_dim=26**3)(inputs_3_gram)
lstm_3_gram = LSTM(lstm_3_gram_embedding)(em_input_3_gram)
concat = concatenate([lstm_2_gram, lstm_3_gram])
output = Dense(output_shape,activation='sigmoid')(concat)

model = Model(inputs=[inputs_2_gram, inputs_3_gram], outputs=[output])
model.compile(optimizer='adam', loss='binary_crossentropy')

model.fit([np_2_gram_in, np_3_gram_in], [np_output], epochs=5)
model.predict([np_2_gram_in,np_3_gram_in])

Upvotes: 1

Related Questions