Natural Language Processing For Text Analysis With Spacy - Udemy

What you'll learn
Understand the basic concepts of natural language processing, including: part-of-speech, lemmatization, stemming, named entity recognition, and stop words
Implement text summarisation and keyword search
Understand more advanced concepts, such as: dependency parsing, tokenization, word and sentence similarity
Implement text summarisation and keyword search
Requirements
Basic Python data science concepts
Basic Python syntax
Description
Natural Language Processing (NLP) is a subfield of Artificial Intelligence (AI) to enable computers to comprehend spoken and written human language. NLP has several applications, including text-to-voice and speech-to-text conversion, chatbots, automatic question-and-answer systems (Q&A), automatic image description creation, and video subtitles. With the introduction of ChatGPT, NLP will become more and more popular, potentially leading to increased employment opportunities in this branch of AI. The SpaCy framework is the workhorse of the Python NLP ecosystem owing to (a) its ability to process large text datasets, (b) information extraction, (c) pre-processing text for subsequent use in AI models, and (d) Developing production-level NLP applications. IF YOU ARE A NEWCOMER TO NLP, ENROLL IN MY LATEST COURSE ON HOW TO LEARN ALL ABOUT NATURAL LANGUAGE PROCESSING (NLP) AND TO DEVELOP NLP MODELS USING SPACYThe course is divided into three main parts:Section 1-2: The course will introduce you to the primary Python concepts you need to build NLP models, including getting started with Google Colab (an online Jupyter implementation which will save the fuss of installing packages on your computers). Then the course will introduce the basic concepts underpinning NLP and the spaCy framework. By this end, you will gain familiarity with NLP theory and the spaCy architecture.Section 3-5: These sections will focus on the most basic natural language processing concepts, such as: part-of-speech, lemmatization, stemming, named entity recognition, stop words, dependency parsing, word and sentence similarity and tokenization and their spaCy implementations.Section 6: You will work through some practical projects to use spaCy for real-world applicationsAn extra section covers some Python data science basics to help you. Why Should You Take My Course?MY COURSE IS A HANDS-ON TRAINING WITH REAL PYTHON SOCIAL MEDIA MINING- You will learn to carry out text analysis and natural language processing (NLP) to gain insights from unstructured text data, including tweets.My course provides a foundation to conduct PRACTICAL, real-life social media mining. By taking this course, you are taking a significant step forward in your data science journey to become an expert in harnessing the power of text for deriving insights and identifying trends.I have an MPhil (Geography and Environment) from the University of Oxford, UK. I also completed a data science intense PhD at Cambridge University (Tropical Ecology and Conservation). I have several years of experience analyzing real-life data from different sources, including text sources, producing publications for international peer-reviewed journals and undertaking data science consultancy work. In addition to all the above, you'll have MY CONTINUOUS SUPPORT to ensure you get the most value out of your investment!ENROLL NOW :)
Overview
Section 1: Introduction To The Course
Lecture 1 Welcome to the Course
Lecture 2 Data and Code
Lecture 3 Python Installation
Lecture 4 Start With Google Colaboratory Environment
Lecture 5 Google Colabs and GPU
Lecture 6 Installing Packages In Google Colab
Section 2: Get Started with Natural Language Processing (NLP) With SpaCy
Lecture 7 What Is spaCy?
Lecture 8 What Is a Doc Object
Lecture 9 Extracting Information From Unstructured Text Data
Lecture 10 Splitting and Cleaning Text
Lecture 11 SpaCy Language Models
Lecture 12 Stop Words
Lecture 13 Lemmitization
Lecture 14 Putting it all together in pipelines
Lecture 15 Adding Components to Pipelines
Section 3: Rules-Based Matching For Information Extraction
Lecture 16 Token Matcher
Lecture 17 Phrase Matcher
Lecture 18 Detect Entities With Entity Ruler
Lecture 19 Lets Locate the Phone Numbers
Lecture 20 Regex Matchers
Lecture 21 Similarity Matching
Section 4: Word Vectors for Linguistic Information
Lecture 22 What Is Semantic Similarity
Lecture 23 Work with word vectors in spaCy
Lecture 24 Semantic Similarity With Entities
Lecture 25 Similarity Comparison With a Keyword
Lecture 26 Using Third-Party Word Vectors
Section 5: Textual Interlinkages
Lecture 27 Concept behind textual interlinkages
Lecture 28 Visualise the dependency between entities
Lecture 29 Looking for specific dependencies
Section 6: Practical Case Studies
Lecture 30 Mining Financial Information Using POS Tagging
Lecture 31 Visualise the Entities
Lecture 32 Extract Organisation Names
Section 7: Some Python Data Science Concepts to Bear In Mind
Lecture 33 What Is Pandas?
Lecture 34 Basic Data Cleaning With Pandas
Lecture 35 Principles of Data Visualisation
Lecture 36 Principal Component Analysis (PCA):Theory
Data Scientists who want to increase their knowledge in natural language processing,Students of Artificial Intelligence (AI),People interested in learning real-world NLP aplications

Homepage

https://www.udemy.com/course/natural-language-processing-for-text-analysis-with-spacy/