I was wondering how Question and Answering (Q&A) systems could be addressed via machine learning? You describe different algorithms in your book, from which some are related to Natural Language processing. Which algorithms are useful to dive into when implementing Q&A systems?
Laura thank you for your question! Yes, see ch18 on Seq2Seq models and see the recent TF2 branch and an implementation using a similar notebook/approach to the TensorFlow Neural MT example (Spanish to English). This is an Encoder / Decoder model that is like a Q&A answer for the Q is a translation. See: https://www.tensorflow.org/tutorials/text/nmt_with_attention