Computational Linguistics - Intermediate Course
Published 12/2024
MP4 | Video: h264, 1920x1080 | Audio: AAC, 44.1 KHz
Language: English | Size: 1.87 GB | Duration: 4h 9m
Published 12/2024
MP4 | Video: h264, 1920x1080 | Audio: AAC, 44.1 KHz
Language: English | Size: 1.87 GB | Duration: 4h 9m
Advancing Your Natural Language Processing Skills
What you'll learn
Apply natural language processing techniques to analyze and extract information from text data
Develop and evaluate machine learning models for text classification and sentiment analysis
Understand and implement common algorithms for syntactic parsing and machine translation
Design and implement a computational linguistics project, including data preprocessing, feature extraction, and model training and evaluation
Do NLP tasks with Generative AI
Requirements
Students should have a basic understanding of linguistic concepts, and basic programming skills, especially in Python. It is also recommended that students have completed the Computational Linguistics - Beginner Course.
Description
Are you ready to take your computational linguistics skills to the next level? This intermediate course dives deep into the foundational concepts of Natural Language Processing (NLP) while introducing advanced tools and techniques used in the field. Designed for students and professionals with basic knowledge of computational linguistics, this course blends solid theory with hands-on workshops to boost your expertise. What You'll Learn:Introduction to NLP: A comprehensive overview of the key concepts underlying Natural Language Processing. Hands-On Workshop with NLTK: Learn how to utilize this powerful Python library for linguistic analysis. Exploring spaCy: Master this modern and efficient tool for large-scale NLP tasks. Regular Expressions: Discover how to use regex for precise and efficient text processing. Working with WordNet: Understand how to leverage this lexical database for semantic analysis and NLP tasks. Generative AI and NLP: The most extensive section of the course, where you'll explore how to harness generative AI models for advanced tasks such as text generation, summarization, sentiment analysis, and more. Why Enroll? This course is designed to be practical and directly applicable. Each section includes interactive examples, guided exercises, and real-world projects to help you confidently tackle computational linguistics challenges. Join today and become proficient in cutting-edge NLP tools and techniques with this comprehensive and up-to-date course!
Overview
Section 1: Introduction
Lecture 1 Introduction
Lecture 2 In the real world
Lecture 3 Strucuture of the course
Section 2: NLP Concepts
Lecture 4 Tokenization
Lecture 5 Lemmatization
Lecture 6 Stemming
Lecture 7 Part-of-Speech (POS) tagging
Lecture 8 Universal POS Tags
Lecture 9 Name Entity Recognition
Lecture 10 NER tags by Microsoft
Lecture 11 Stopwords Removal
Lecture 12 Sentiment Analysis
Section 3: Library: NLTK
Lecture 13 ipynb file NLTK
Lecture 14 What is NLTK?
Lecture 15 Getting the text to work with
Lecture 16 IDE Installation
Lecture 17 Tokenization with NLTK
Lecture 18 Lemmatization with NLTK
Lecture 19 Stemming with NLTK
Lecture 20 POS Tagging with NLTK
Lecture 21 Name Entity Recognition with NLTK
Lecture 22 Stopwords with NLTK
Lecture 23 Sentiment Analysis with NLTK
Section 4: Library: spaCy
Lecture 24 ipynb file spaCy
Lecture 25 What is spaCy?
Lecture 26 Tokenization with spaCy
Lecture 27 Lemmatization with spaCy
Lecture 28 POS Tagging with spaCy
Lecture 29 Name Entity Recognition with spaCy
Lecture 30 Sentiment Analysis with spaCy
Section 5: Library: Regular expressions
Lecture 31 Introduction
Lecture 32 Structure
Lecture 33 User of r" "
Lecture 34 Methods
Lecture 35 Methods for Match objects
Lecture 36 Exercise 1
Lecture 37 Solving Exercise 1
Lecture 38 Indentifiers
Lecture 39 Exercise 2
Lecture 40 Solving Exercise 2
Lecture 41 Metacharacters
Lecture 42 Exercise 3
Lecture 43 Solving Exercise 3
Lecture 44 Exercise 4
Lecture 45 Solving Exercise 4
Lecture 46 Quantifiers
Lecture 47 Exercise 5
Lecture 48 Solving Exercise 5
Lecture 49 Sets
Lecture 50 Modification
Lecture 51 Exercise 6
Lecture 52 Solving Exercise 6
Lecture 53 Exercise 7
Lecture 54 Solving Exercise 7
Lecture 55 Exercise 8
Lecture 56 Solving Exercise 8
Section 6: NLP tasks with Generative AI
Lecture 57 Getting started
Lecture 58 Getting our source text
Lecture 59 Getting our keys
Lecture 60 Checking official documentation
Lecture 61 Lemmatization with Generative AI
Lecture 62 POS Tagging with Generative AI
Lecture 63 Named Entity Recognition with Generative AI
Lecture 64 Sentiment Analysis with Generative AI
Lecture 65 Tailored responses based on sentiment with Generative AI
Section 7: Extra: Wordnet
Lecture 66 Introduction
Lecture 67 Main methods
Lecture 68 Applying methods to the code
Lecture 69 More moethods
Lecture 70 Exercise 1
Lecture 71 Exercise 1: Solved
Section 8: Conclusion
Lecture 72 Conclusion
This course is designed for linguists, translators, and other students with a background in linguistic-related studies who are interested in learning more about computational linguistics and natural language processing. If you have a basic understanding of Python, you will be able to follow along and apply the techniques covered in this course. If you are new to Python, don't worry! We recommend starting with the Computational Linguistics - Beginner Course to build a strong foundation before moving on to this intermediate-level course.