Genre: eLearning | MP4 | Video: h264, 1280x720 | Audio: aac, 44100 Hz
Language: English | VTT | Size: 9.54 GB | Duration: 2 section | 273 lectures | (27h 48m)
Welcome to KGP Talkie's Natural Language Processing course.
What you'll learn
Learn complete text processing with Python
Learn how to extract text from PDF files
Use Regular Expressions for search in text
Use SpaCy and NLTK to extract complete text features from raw text
Use Latent Dirichlet Allocation for Topic Modelling
Use Scikit-Learn and Deep Learning for Text Classification
Learn Multi-Class and Multi-Label Text Classification
Use Spacy and NLTK for Sennt Analysis
Understand and Build word2vec and GloVe based ML models
Use Gensim to obtain pretrained word vectors and compute similarities and analogies
Learn Text Summarization and Text Generation using LSTM and GRU
Have a desire to learn
Elementary level math
Have basic understanding of Python and Machine Learning
It is designed to give you a complete understanding of Text Processing and Mining with the use of State-of-the-Art NLP algorithms in Python.
We will learn Spacy in details and we will also explore the uses of NLP in real-life. This course covers the basics of NLP to advance topics like word2vec, GloVe, Deep Learning for NLP like CNN, ANN, and LSTM. I will also show you how you can optimize your ML code by using various tools of sklean in python. At the end part of this course, you will learn how to generate poetry by using LSTM. Multi-Label and Multi-class classification is explained. At least 12 NLP Projects are covered in this course. You will learn various ways of solving edge cutting NLP problems.
In this course, we will start from level 0 to the advanced level.
We will start with basics like what is machine learning and how it works. Thereafter I will take you to Python, Numpy, and Pandas crash course. If you have prior experience you can skip these sections. The real game of NLP will start with Spacy Introduction where I will take you through various steps of NLP preprocessing. We will be using Spacy and NLTK mostly for the text data preprocessing.
In the next section, we will learn about working with Files for storing and loading the text data. This section is the foundation of another section on Complete Text Preprocessing. I will show you many ways of text preprocessing using Spacy and Regular Expressions. Finally, I will show you how you can create your own python package on preprocessing. It will help us to improve our code writing skills. We will be able to reuse our code systemwide without writing codes for preprocessing every . This section is the most important section.
Then, we will start the Machine learning theory section and a walkthrough of the Scikit-Learn Python package where we will learn how to write clean ML code. Thereafter, we will develop our first text classifier for SPAM and HAM message classification. I will be also showing you various types of word embeddings used in NLP like Bag of Words, Term Frequency, IDF, and TF-IDF. I will show you how you can estimate these features from scratch as well as with the help of the Scikit-Learn package.
Thereafter we will learn about the machine learning model deployment. We will also learn various other important tools like word2vec, GloVe, Deep Learning, CNN, LSTM, RNN etc.
At the end of this lesson, you will learn everything which you need to solve your own NLP problem.
Who this course is for:
Bners in Natural Language Processing
Data Scientist curious to learn NLP