tf.data with multiple inputs / outputs in Keras

I'm not using Keras but I would go with an tf.data.Dataset.from_generator() - like:

def _input_fn():
  sent1 = np.array([1, 2, 3, 4, 5, 6, 7, 8], dtype=np.int64)
  sent2 = np.array([20, 25, 35, 40, 600, 30, 20, 30], dtype=np.int64)
  sent1 = np.reshape(sent1, (8, 1, 1))
  sent2 = np.reshape(sent2, (8, 1, 1))

  labels = np.array([40, 30, 20, 10, 80, 70, 50, 60], dtype=np.int64)
  labels = np.reshape(labels, (8, 1))

  def generator():
    for s1, s2, l in zip(sent1, sent2, labels):
      yield {"input_1": s1, "input_2": s2}, l

  dataset = tf.data.Dataset.from_generator(generator, output_types=({"input_1": tf.int64, "input_2": tf.int64}, tf.int64))
  dataset = dataset.batch(2)
  return dataset

...

model.fit(_input_fn(), epochs=10, steps_per_epoch=4)

This generator can iterate over your e.g text-files / numpy arrays and yield on every call a example. In this example, I assume that the word of the sentences are already converted to the indices in the vocabulary.

Edit: Since OP asked, it should be also possible with Dataset.from_tensor_slices():

def _input_fn():
  sent1 = np.array([1, 2, 3, 4, 5, 6, 7, 8], dtype=np.int64)
  sent2 = np.array([20, 25, 35, 40, 600, 30, 20, 30], dtype=np.int64)
  sent1 = np.reshape(sent1, (8, 1))
  sent2 = np.reshape(sent2, (8, 1))

  labels = np.array([40, 30, 20, 10, 80, 70, 50, 60], dtype=np.int64)
  labels = np.reshape(labels, (8))

  dataset = tf.data.Dataset.from_tensor_slices(({"input_1": sent1, "input_2": sent2}, labels))
  dataset = dataset.batch(2, drop_remainder=True)
  return dataset

One way to solve your issue could be to use the zip dataset to combine your various inputs:

sent1 = np.array([1, 2, 3, 4, 5, 6, 7, 8], dtype=np.float32)
sent2 = np.array([20, 25, 35, 40, 600, 30, 20, 30], dtype=np.float32)
sent1 = np.reshape(sent1, (8, 1, 1))
sent2 = np.reshape(sent2, (8, 1, 1))

labels = np.array([40, 30, 20, 10, 80, 70, 50, 60], dtype=np.float32)
labels = np.reshape(labels, (8, 1))

dataset_12 = tf.data.Dataset.from_tensor_slices((sent_1, sent_2))
dataset_label = tf.data.Dataset.from_tensor_slices(labels)

dataset = tf.data.Dataset.zip((dataset_12, dataset_label)).batch(2).repeat()
model.fit(dataset, epochs=10, steps_per_epoch=4)

will print: Epoch 1/10 4/4 [==============================] - 2s 503ms/step...