6FINDING PATTERNS AND WALKING DEPENDENCY TREES
If you want your application to categorize a text, extract specific phrases from it, or determine how semantically similar it is to another text, it must be able to “understand” an utterance submitted by a user and generate a meaningful response to it.
You’ve already learned some techniques for performing these tasks. This chapter discusses two more approaches: using word sequence patterns to classify and generate text, and walking the syntactic dependency tree of an utterance to extract necessary pieces of information from it. I’ll introduce you to spaCy’s Matcher tool to find patterns. I’ll also ...
Get Natural Language Processing with Python and spaCy now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
