Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Subscribe
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Natural language processing
Rating: 4.0 out of 5(2 ratings)
376 students

Natural language processing

text processing, tokenization
Created bySankara Narayanan S
Last updated 7/2025
English
English [Auto],

What you'll learn

  • understand the fundamentals behind the Language processing and perform word level analysis
  • understand the syntactic processing and probabilistic context-free grammars
  • conceive the basics of the knowledge representation, inference, and discourse analysis
  • recognize the significance of transformer-based models

Course content

4 sections • 13 lectures • 2h 43m total length

  • Introduction10:51

    Learn how natural language processing enables machines to understand human language. Follow steps like sentence segmentation, word tokenization, part-of-speech tagging, lemmatization, stopword removal, dependency parsing, and coreference resolution.

  • Phases of natural language processing16:55

    Discover the five phases of natural language processing, from lexical and morphological analysis to disclosure integration. Learn key steps like tokenization, pos tagging, stemming, lemmatization, and parsing.

  • Term frequency and inverse document frequency11:07

    Explore tf-idf in natural language processing by learning term frequency and inverse document frequency, how they combine to score word relevance across documents with practical examples.

  • N grams7:30

    Explore n-grams in natural language processing, from unigrams to five-grams, to capture context and enhance language models, predictions, and information retrieval.

  • Lemmatization6:42

    Lemmatization groups inflected forms into base lemmas in natural language processing, unlike stemming, and uses rule-based, dictionary-based, or machine-learning approaches with examples like walked to walk and went to go.

  • Named entity recognition(NER)10:26

    Discover how named entity recognition identifies and classifies entities in unstructured text, transforming it into structured data for applications like text summarization and knowledge graphs.

Requirements

  • Basic computer knowledge

Description

This course provides a comprehensive introduction to Natural Language Processing (NLP) – a field at the intersection of computer science, artificial intelligence, and linguistics that focuses on the interaction between computers and human language.

Students will learn how machines process, analyze, and understand human language through text and speech. The course covers key NLP techniques such as text preprocessing, tokenization, part-of-speech tagging, named entity recognition, sentiment analysis, language modeling, and text classification. Through a series of projects and assignments, learners will get experience building real-world NLP applications such as:

  • Text summarizers

  • Spam filters

  • Sentiment analysis tools

  • Question answering systems

  • Chatbots

Key Topics Covered:

  • Basics of Natural Language Processing

  • Phases of NLP

  • Text Preprocessing (Tokenization, Stemming, Lemmatization, Stop word Removal)

  • Part-of-Speech (POS) Tagging

  • Feature extraction

  • Term frequency

  • Inverse document frequency

  • Named Entity Recognition (NER)

  • Sentiment Analysis

  • Text Classification

  • Language Modeling (n-grams, word embeddings)

  • recurrent neural networks

  • Long short term memory

  • Attention mechanisms

  • transformer based models

  • Introduction to Deep Learning for NLP (using RNNs, LSTMs, Transformers)

  • Practical Projects: Chatbots, Text Summarization, Machine Translation

  • By the end of this course, learners will be able to:

    • Understand the core concepts and challenges in Natural Language Processing.

    • Apply text preprocessing techniques (tokenization, stemming, stopword removal).

    • Implement feature extraction methods like Bag of Words (BoW), TF-IDF, and word embeddings (Word2Vec, GloVe).

    • Build and evaluate machine learning models for text classification and sentiment analysis.

    • Work with named entity recognition (NER) and part-of-speech (POS) tagging.

    • Develop language models and understand sequence modeling using RNNs, LSTMs, and transformer models.

    • Fine-tune and use pre-trained models like BERT for downstream NLP tasks.

Who this course is for:

  • Undergraduate students with basic computer knowledge

Report abuse