Overview: Designing a Chatbot with spaCy

In this chapter, we will use everything we have learned so far to design a chatbot. We will perform entity extraction, intent recognition, and context handling. We will use different ways of syntactic and semantic parsing, entity extraction, and text classification.

First, we'll explore the dataset we'll use to collect linguistic information about the utterances within it. Then, we'll perform entity extraction by combining the spaCy named entity recognition (NER) model and the spaCy Matcher class. After that, we'll perform intent recognition with two different techniques: a pattern-based method and statistical text classification with TensorFlow and Keras. We'll train a character-level LSTM to classify the utterance intents.