![]() ![]() The IN attribute allows a list of terms and means that any of those words in the list, along with the word ‘pizza’ are matched. ![]() To create a match pattern for something- let’s say “loves pizza” - I would write the following code: spaCy uses Python to do this with patterns that can be created, added to a spaCy Matcher object, and then used against text to find matches.įor example, let’s say I want to find the words “loves to eat pizza” and I know from researching it that people often use that exact phrase but also “loves pizza”, “love pizza”, “digs pizza”, “devours pizza”, and “eat pizza” all to mean loves pizza (because everyone who eats pizza loves pizza, right?). One specific way of using tokens is in matching them against explicit criteria. One of the core ideas in spaCy (really NLP) is that words are broken down into tokens and those tokens can be identified (e.g., parts of speech) or used in various ways. Separately, it’s also a data scientist’s dream because of how the underlying NLP can be enhanced (still a weird dream)! I get to use it almost every day and along the way, I’ve picked up a few tricks you might find helpful, the first involves reusable terms. ![]() It’s an ML engineer’s dream (what a weird dream though). I’m not gonna lie, I really dig spaCy it’s based on sophisticated natural language processing (NLP) but is incredibly simple to use. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |