In this course you will build MULTIPLE practical systems using natural language processing, or NLP - the branch of machine learning and data science that deals with text and speech. This course is not part of my deep learning series, so there are no mathematical prerequisites - just straight up coding in Python. All the materials for this course are FREE.
After a brief discussion about what NLP is and what it can do, we will begin building very useful stuff. The first thing we'll build is a spam detector. You likely get very little spam these days, compared to say, the early 2000s, because of systems like these.
Next we'll build a model for sentiment analysis in Python. This is something that allows us to assign a score to a block of text that tells us how positive or negative it is. People have used sentiment analysis on Twitter to predict the stock market.
We'll go over some practical tools and techniques like the NLTK (natural language toolkit) library and latent semantic analysis or LSA.
Finally, we end the course by building an article spinner. This is a very hard problem and even the most popular products out there these days don't get it right. These lectures are designed to just get you started and to give you ideas for how you might improve on them yourself. Once mastered, you can use it as an SEO, or search engine optimization tool. Internet marketers everywhere will love you if you can do this for them!
This course focuses on "how to build and understand", not just "how to use". Anyone can learn to use an API in 15 minutes after reading some documentation. It's not about "remembering facts", it's about "seeing for yourself" via experimentation. It will teach you how to visualize what's happening in the model internally. If you want more than just a superficial look at machine learning models, this course is for you.
All the code for this course can be downloaded from my github: /lazyprogrammer/machine_learning_examples
In the directory: nlp_class
Make sure you always "git pull" so you have the latest version!
HARD PREREQUISITES / KNOWLEDGE YOU ARE ASSUMED TO HAVE:
TIPS (for getting through the course):
USEFUL COURSE ORDERING:
NLP is very practical, so it's worth listing out what it is used for. Here we give brief overviews of things like spam detection, POS tagging, NER, sentiment analysis, machine translation, summarization, the Turing test, and more.
In this lecture some examples of ambiguity of language are given, to make it clear why NLP is not a straightforward problem.
In addition to the word frequencies we looked at previously, this lecture looks at bag-of-words in general and different ways to implement that, including raw counts and binary indicator variables. We also briefly mention TF-IDF.
What is sentiment analysis? In this lecture we'll look at the data we'll be using to build our sentiment analysis tool, and talk about how we can manually pre-process the data so that we can plug it into a machine learning classifier.
In this lecture we'll write our sentiment analyzer in Python to predict sentiment on Amazon reviews.
How do we tag the tokens of a sentence by their parts-of-speech? i.e. Is this token a noun, verb, adjective, adverb, or something else?
How do we turn words into their "base form"? i.e. plural to singular
Can we also tag parts of a sentence as a "person", "organization", or "location"?
What is synonymy and polysemy and how can LSA / LSI help?
What is article spinning and how is it related to search engines, SEO (search engine optimization), and Internet marketing?
What will be our strategy for creating an article spinner? We'll create a trigram model.
I am a data scientist, big data engineer, and full stack software engineer.
For my masters thesis I worked on brain-computer interfaces using machine learning. These assist non-verbal and non-mobile persons communicate with their family and caregivers.
I have worked in online advertising and digital media as both a data scientist and big data engineer, and built various high-throughput web services around said data. I've created new big data pipelines using Hadoop/Pig/MapReduce. I've created machine learning models to predict click-through rate, news feed recommender systems using linear regression, Bayesian Bandits, and collaborative filtering and validated the results using A/B testing.
I have taught undergraduate and graduate students in data science, statistics, machine learning, algorithms, calculus, computer graphics, and physics for students attending universities such as Columbia University, NYU, Humber College, and The New School.