The main goal of NLP is to understand the meaning of text; and sentiment analysis of text is one of the important applications of NLP. Natural Languages have evolved from thousands of years of human existence as they pass from generation to generation. The grammar of any natural language is complex and different from other languages. Moreover, it is evolutionary. This makes Natural Language Processing (NLP) a complex challenge.
The main goal of NLP is to understand the meaning of text; and sentiment analysis of text is one of the important applications of NLP. Natural Languages have evolved from thousands of years of human existence as they pass from generation to generation. The grammar of any natural language is complex and different from other languages. Moreover, it is evolutionary. This makes Natural Language Processing (NLP) a complex challenge.
Program Experience
Through hands-on activities, you will cover fundamental mathematical analysis of language and build your critical understanding of popular services such as Google Cloud Platform and IBM Watson, among others, for Natural Language Processing.
First, we will cover the fundamental mathematical analysis of NLP. You will write Python code to access NLTK, TextBlob, and spaCy software packages. Next, You will learn how text can be tokenized using regular expressions, NLTK, and TextBlob. You will learn how text tokens are converted into vectors and how the vectorization process, including count vectorizer, cosine similarity computation, and TF-IDF (Term Frequency Inverse Document Frequency), is used. Finally, we will cover how text semantics can be analyzed using Latent Semantic Analysis (LSA) and Latent Dirichlet Allocation (LDA).
In the second approach, you will explore the Machine/Deep Learning models for NLP. We will create Naïve Bayes machine learning models for document classification. Learn how Deep learning tools can generate Word Embeddings like Word2Vec. Next, you will learn how to employ transformers, including GPT and BERT, for semantic analysis of text.
By completing this short course and either the Machine Learning for Advanced Analytics course or the Deep Learning with TensorFlow course, you will be eligible to receive the Caltech CTME Machine Learning for Advanced Analytics Certificate.
Benefits
You will learn how to build competency in:
Analysis of text to understand the meaning of the text
Social Media (Twitter) data analysis for customer sentiment analysis
Text-based customer feedback data analysis
Language Detection + Translation
Inflection: Pluralization + Singularization
Normalization: Stemming + Lemmatization
Semantics using nGrams
Entity Recognition: spaCy
Similarity Detection: spaCy
Topics
Software Based NLP
Analysis of Words + Sentences + Semantics + Polarity + Subjectivity
Tokenization
Vectorization
Semantic Analysis
Machine Learning Models
Laplace Smoothing
Word Embeddings
Language Models
GPT 1/2/3
Who Should Attend
Writers. Those who write content for websites, blogs, and documentation.
Digital Marketing Professionals. Those who write website content optimized for Search Engine Optimization (SEO) will find the course beneficial. The participants can analyze social media chatter to measure customers' sentiments regarding products/services and the corporation’s image.
Language Translators. Those involved in translation services from one language to another are used heavily in the legal profession and industry for corporate documentation.
Software and Hardware Professionals. Those currently working in the field of robotics and personal assistant appliances will find the course content to be relevant.
Schedule
Course
Duration
Hybrid Online (via Zoom)
Natural Language Processing (NLP) 10.0
There are 4 hours of instruction every Saturday for 6 Days, totaling 24 instruction hours.
During the week before each session you will receive emails containing location-specific instructions.
On the following Saturdays
November 4, 11, 18, December 2, 9, 16, 2023
Sat 8 AM - 12 PM Pacific Time
Instructors
Ash Pahwa
Advanced Analytics, Machine Learning, AI Programming
