October 2018
Intermediate to advanced
472 pages
10h 57m
English
This chapter builds directly on Chapter 4, Build NLP Pipeline for Building Chatbots to build a more advanced chatbot for our hypothetical restaurant chain to automate the process of fielding call in orders. We combined our learning on a number of technologies to make a chatbot that is more contextually aware and robust. We avoided some of the limitations of CNNs in chatbots by building a recurrent neural network (RNN) model with long short-term memory (LSTM) units, specifically designed to capture the signal represented in sequences of characters or words.
We implemented a language model, with an encoder-decoder RNN based on the LSTM unit, for a simple sequence-to-sequence question-answer ...
Read now
Unlock full access