In this chapter, we step into the messy world of human language. We’ll start by discussing the differences between language and math that make language algorithms difficult. We’ll continue by building a space insertion algorithm that can take any text in any language and insert spaces wherever they’re missing. After that, we’ll build a phrase completion algorithm that can imitate the style of a writer and find the most fitting next word in a phrase.
The algorithms in this chapter rely heavily on two tools that we haven’t used before: list comprehensions and corpuses. List comprehensions enable us to quickly generate lists using ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month, and much more.
