Course 1 : Natural Language Processing (NLP) – Primer – AI school

About Course

Natural Language Processing (NLP) is a subfield of artificial intelligence (AI) and linguistics that focuses on the interaction between computers and humans using natural language.

It involves the development of algorithms and techniques to enable computers to understand, interpret, and generate human language in a meaningful way.

Course Content

NLP – overview & Basic processing

Quick introduction on NLP
Standard tokenization techniques
Advanced tokenization methods
Stemming and Lemmatization
Parts of speech and it’s usage in NLP
Other Key pre-processing steps

Understanding Regular Expressions (Regex)
Understanding regular expressions (regex) is crucial for anyone working with text processing, pattern matching, or data extraction tasks.

Introduction to Regular Expressions
Literal Characters:
Metacharacters and Escaping
Character Classes
Anchors
Quantifiers
Grouping and Capturing
Alternation
Assertions
Modifiers
Common Use Cases

n-grams in NLP

Key phrase Extraction

Overview on Key phrase extraction
frequency distribution and cumulative distribution
bi-grams and tri-grams using NLTK
Count of Nouns in Text using NLTK
Extract Nouns using spaCy
How Co-occurrence Matrix Works
Understand Collocations using NLTK
Extract Key Phrases using RAKE
Use Rules Matchers in spaCy

Named Entity recognition and Linking

Vectorization & Embedding

Intro on vectorization – Start with count vectorizer

28:57
Detailed coverage on TF-IDF vectors

21:50
Count & TF-IDF vectorizer for online ML models

07:04
Hashing vectors for online ML models

24:59
Beyond TF-IDF: Exploring BM25 for Enhanced Document Ranking and Vectorization

29:57
From Words to Vectors : Understanding Word2Vec Embeddings

31:21
Constructing Training Set for Word Embedding Algorithms

13:19
Understanding Text Embedding Layers in Keras/TensorFlow

16:54
Transforming Words into Vectors: Hands on with Gensim’s Word2Vec

21:18
Hands-on guide on Word2Vec: Gensim’s Hierarchical Softmax Strategies

28:37
Optimizing Word Vector Generation: A Gensim Word2Vec Approach with Negative Sampling

00:00
From Words to Documents: Understanding Doc2Vec with Gensim

00:00
Overview on GLOVE vectors
Understanding on FastText vectors

Topic Modeling

Student Ratings & Reviews

No Review Yet

About Course

Course Content

NLP – overview & Basic processing

Quick introduction on NLP

Standard tokenization techniques

Advanced tokenization methods

Stemming and Lemmatization

Parts of speech and it’s usage in NLP

Other Key pre-processing steps

Understanding Regular Expressions (Regex) Understanding regular expressions (regex) is crucial for anyone working with text processing, pattern matching, or data extraction tasks.

Introduction to Regular Expressions

Literal Characters:

Metacharacters and Escaping

Character Classes

Anchors

Quantifiers

Grouping and Capturing

Alternation

Assertions

Modifiers

Common Use Cases

n-grams in NLP

what are n-grams

n-grams in Language models

n-grams in text generation & synonym expansion

Key phrase Extraction

Overview on Key phrase extraction

frequency distribution and cumulative distribution

bi-grams and tri-grams using NLTK

Count of Nouns in Text using NLTK

Extract Nouns using spaCy

How Co-occurrence Matrix Works

Understand Collocations using NLTK

Extract Key Phrases using RAKE

Use Rules Matchers in spaCy

Named Entity recognition and Linking

Introduction to NER

NER using NLTK (Natural Language Toolkit)

NER using Spacy

Using Gensim

Vectorization & Embedding

Intro on vectorization – Start with count vectorizer

Detailed coverage on TF-IDF vectors

Count & TF-IDF vectorizer for online ML models

Hashing vectors for online ML models

Beyond TF-IDF: Exploring BM25 for Enhanced Document Ranking and Vectorization

From Words to Vectors : Understanding Word2Vec Embeddings

Constructing Training Set for Word Embedding Algorithms

Understanding Text Embedding Layers in Keras/TensorFlow

Transforming Words into Vectors: Hands on with Gensim’s Word2Vec

Hands-on guide on Word2Vec: Gensim’s Hierarchical Softmax Strategies

Optimizing Word Vector Generation: A Gensim Word2Vec Approach with Negative Sampling

From Words to Documents: Understanding Doc2Vec with Gensim

Overview on GLOVE vectors

Understanding on FastText vectors

Topic Modeling

Introduction to Topic Modeling

Probabilistic Topic Models

Non-Probabilistic Topic Models

Algorithms and Implementation

Evaluation Metrics

Applications of Topic Modeling

Challenges and Limitations:

Student Ratings & Reviews

Understanding Regular Expressions (Regex)
Understanding regular expressions (regex) is crucial for anyone working with text processing, pattern matching, or data extraction tasks.