4.83 (3 reviews)
☑ Natural Language Processing (NLP)
☑ TextBlob -- a Python framework built on top of NLTK
☑ Text classification
☑ Part-of-speech tagging
☑ Producing definitions
☑ Comparing the similarity of words
☑ Generating n-grams
☑ Spell checking
☑ Sentiment analysis
☑ Hugging Face's Datasets library
TextBlob is an open-source Python package built on top of NLTK, which is perhaps the most well-known NLP framework. TextBlob allows you to complete common NLP tasks with just a few lines of code and with minimal complexities. So, whether you're a beginner looking to learn NLP or a professional who wants to learn a tool to simplify your life -- this course is for you.
TextBlob is one of the most popular NLP Python packages with over 7700 stars on GitHub and over 10M downloads.
This course will cover:
Comparing the similarity of words
Fetching data from Hugging Face's dataset distribution network
AND MORE ALL WITH TEXTBLOB!!
NONE!!! This is done entirely in Google Colab, which is web based.
About the instructor:
My name is Eric Fillion, and I’m from Canada. I’m on a mission to make state-of-the-art advances in the field of NLP through creating open-source tools and by creating educational content. In early 2020, I led a team that launched an open-source Python Package called Happy Transformer. Happy Transformer allows programmers to implement and train state-of-the-art Transformer models with just a few lines of code. Since its release, it has won awards and has been downloaded over 17k times.
A basic understanding of Python
A google account -- for Google Colab
I've made all of the introductory lectures for each section available for free preview. So, check them out, and I'm looking forward to seeing you in the course!
Section 2 Introduction
Section 2 Links
Create a TextBlob
Section 2 Challenge
Section 3 Introduction
Section 3 Links
Section 3 Challenge
Fundmental NLP Tasks
Section 4 Introduction
Section 4 Links
Section 4 Challenge
Section 5 Introduction
Section 5 Links
Get/Format Data With Hugging Face's Datasets Library
Train a Model
Section 5 Challenge