Summary
In this chapter, we’ve learned several important skills that make use of rules for processing natural language.
We’ve learned how to apply regular expressions to identify fixed-format expressions such as numbers, dates, and addresses. We’ve also learned about the uses of rule-based Python tools such as the NLTK syntactic parsing libraries for analyzing the syntactic structure of sentences and how to apply them. Finally, we’ve learned about rule-based tools for semantics analysis such as spaCy’s entity_ruler for analyzing the slot-value semantics of sentences.
The next chapter, Chapter 9, will begin the discussion on machine learning by introducing statistical techniques such as classification with Naïve Bayes and term frequency-inverse document frequency (TF-IDF), support vector machines (SVMs), and conditional random fields. In contrast to the rule-based approaches we have discussed in this chapter, statistical approaches are based...
