Natural Language Processing and Capstone Assignment

University of California, Irvine via Coursera

Coursera based on 43 ratings

Likes

Overview

"Natural Language Processing and Capstone Assignment" is an advanced course designed to deepen learners' understanding of Natural Language Processing (NLP) techniques and their practical applications. Ideal for students, data scientists, and AI enthusiasts, this course covers key NLP concepts such as text preprocessing, sentiment analysis, language modeling, named entity recognition, and machine translation. The course blends theoretical foundations with hands-on experience, guiding participants through building NLP models using popular Python libraries like NLTK, spaCy, and transformers. Emphasis is placed on leveraging...

Syllabus

Natural Language Processing I

Welcome to Module 1, Natural Language Processing I. In this module we will begin with an introduction to text analytics, or natural language processing (NLP). We will explore the numerous applications of NLP and discuss one of the most popular applications - sentiment analysis.

Natural Language Processing II

Welcome to Module 2, Natural Language Processing II. In this module we will continue our exploration of natural language processing with a review of topic modeling and one of the most effective topic detection techniques currently in use - Latent Dirichlet allocation (LDA). In addition, we will define several technical terms and concepts commonly used in text mining.

The Past, Present, and Future of Data Science I

Welcome to Module 3, Past, Present, and Future of Data Science I. In this module we will provide a historical perspective of the terminology applied to data analytics, as well as a forward-looking discussion of several key trends emerging in data science. We will also explore several leading-edge enablers and enhancers of data science, including deep learning, explainable AI, and automated machine learning.

The Past, Present, and Future of Data Science II

Welcome to Module 4, Past, Present, and Future of Data Science II. In this module we will continue our exploration of new practices in data science and predictive modelling, including model ensembles, sensor technologies and IoT, geospatial analytics, and cloud computing. We will conclude this program with an activity to bring everything youve learned in this program together to develop a data analytics plan.