What you will learn

• NLP scope and challenges
• Levels of language processing
• Tokenization
• Normalization
• Stemming
• Lemmatization
• Stop-word removal
• Regular expressions
• POS tagging
• Context-Free Grammar
• Syntactic parsing
• Named Entity Recognition
• Word Sense Disambiguation
• N-gram language models
• Smoothing
• Bag of Words
• TF-IDF
• Naive Bayes text classification
• Sentiment analysis
• Information extraction
• Text summarization
• Word2Vec
• Deep learning for NLP
• Transformers
• Large Language Models
• Machine translation
• Question answering
• Chatbots
• Speech assistants
• Generative AI

Course content (39 lessons)

1. About This Course — Natural Language Processing — University Course This course covers Natural Language Processing (NLP) as taught in undergraduate/postgraduate BCA/MCA/BTech university courses. The…
2. Unit 1 — Introduction to NLP: Scope, Challenges & Applications — Introduction to Natural Language Processing Natural Language Processing (NLP) is the branch of Artificial Intelligence concerned with enabling computers to read, understand,…
3. Unit 1 — Levels of Language Processing: Morphological & Lexical — Levels of Language Processing Human language can be analysed at several distinct levels , from the smallest meaningful unit up to full documents. An NLP system typically processes…
4. Unit 1 — Levels of Language Processing: Syntactic & Semantic — Syntactic and Semantic Analysis Syntactic Analysis (Parsing) Syntax concerns how words combine to form grammatically correct sentences. Syntactic analysis checks a sentence…
5. Unit 1 — Levels of Language Processing: Discourse & Pragmatic — Discourse and Pragmatic Analysis Discourse Analysis While semantic analysis handles the meaning of a single sentence, discourse analysis studies meaning across multiple connected…
6. Unit 1 — Text Preprocessing: Tokenization — Text Preprocessing — Tokenization Raw text is unstructured and noisy. Before any NLP model can use it, text must go through a preprocessing pipeline . The first step is almost…
7. Unit 1 — Text Preprocessing: Normalization — Text Preprocessing — Normalization Text normalization converts text into a single, consistent, canonical form so that different surface variations of the "same" content are…
8. Unit 1 — Text Preprocessing: Stemming — Text Preprocessing — Stemming Stemming reduces a word to its root/stem form by chopping off suffixes (and sometimes prefixes) using heuristic rules — without necessarily producing…
9. Unit 1 — Text Preprocessing: Lemmatization — Text Preprocessing — Lemmatization Lemmatization reduces a word to its lemma — the dictionary/base form — using vocabulary and morphological (grammatical) analysis, unlike…
10. Unit 1 — Text Preprocessing: Stop-word Removal — Text Preprocessing — Stop-word Removal Stop words are extremely common words (articles, prepositions, pronouns, conjunctions) that carry little topical/semantic meaning on their…
11. Unit 1 — Regular Expressions for NLP — Regular Expressions for NLP Regular expressions (regex) are patterns used to match, search, extract, and substitute text — an indispensable tool throughout the NLP preprocessing…
12. Unit 1 — Building a Complete Text Preprocessing Pipeline — Building a Complete Text Preprocessing Pipeline Now that we've covered tokenization, normalization, stemming, lemmatization, stop-word removal, and regex, let's assemble them into…
13. Unit 2 — Part-of-Speech (POS) Tagging: Introduction & Tagsets — Part-of-Speech (POS) Tagging POS tagging is the process of assigning a grammatical category (noun, verb, adjective, etc.) to every token in a sentence, based on both its…
14. Unit 2 — POS Tagging Methods: Rule-Based, Stochastic & HMM — POS Tagging Methods There are three broad families of POS tagging approaches: rule-based , stochastic (probabilistic) , and hybrid/neural . Modern taggers (like the one used by…
15. Unit 2 — Context-Free Grammar (CFG): Introduction — Introduction to Context-Free Grammar (CFG) A grammar is a set of rules that defines which sequences of words form valid sentences in a language. A Context-Free Grammar (CFG) is…
16. Unit 2 — Syntactic Parsing: Top-Down, Bottom-Up & CYK Algorithm — Syntactic Parsing Algorithms Parsing is the process of analyzing a sentence according to a grammar and producing its parse tree(s). Given a CFG (Unit 2, previous lesson), there…
17. Unit 2 — Named Entity Recognition (NER): Concepts & Techniques — Named Entity Recognition (NER) Named Entity Recognition (NER) identifies and classifies "named entities" in text into predefined categories — people, organizations, locations,…
18. Unit 2 — Named Entity Recognition: Hands-on with spaCy — Named Entity Recognition — Hands-on NER with spaCy (Industry-Standard, Pre-trained) Visualizing Entities NER with NLTK (Chunking-based) Extracting Only PERSON and ORG Entities…
19. Unit 2 — Word Sense Disambiguation (WSD) — Word Sense Disambiguation (WSD) Word Sense Disambiguation (WSD) is the task of determining which meaning (sense) of a word is intended, given the context it appears in — the…
20. Unit 2 — Introduction to Language Models — Introduction to Language Models A language model (LM) is a system that assigns a probability to a sequence of words — modeling how likely that sequence is to occur in the…
21. Unit 2 — N-gram Models — N-gram Language Models An n-gram is a contiguous sequence of n tokens from a piece of text. N-gram models estimate the probability of a word based on the previous n-1 words (the…
22. Unit 2 — Smoothing Techniques for N-gram Models — Smoothing Techniques for N-gram Models As shown in the previous lesson, raw Maximum Likelihood Estimation (MLE) assigns zero probability to any n-gram unseen during training —…
23. Unit 3 — Feature Extraction: Introduction, Need & Importance — Feature Extraction — Introduction, Need & Importance Machine learning algorithms (Naïve Bayes, SVM, logistic regression, neural networks) cannot operate on raw text directly —…
24. Unit 3 — Bag of Words (BoW) — Bag of Words (BoW) Bag of Words (BoW) represents a document as a vector of word counts , completely ignoring word order and grammar — the document is treated as an unordered "bag"…
25. Unit 3 — TF-IDF (Term Frequency–Inverse Document Frequency) — TF-IDF (Term Frequency–Inverse Document Frequency) Plain Bag-of-Words treats every word's raw count as equally meaningful — but common words like "the" appear frequently…
26. Unit 3 — Naïve Bayes for Text Classification — Naïve Bayes for Text Classification Naïve Bayes is a probabilistic classifier based on Bayes' Theorem , with a "naïve" assumption that all features (words) are conditionally…
27. Unit 3 — Text Classification: End-to-End Pipeline — Text Classification — End-to-End Pipeline This lesson combines everything from Units 1–3 so far — preprocessing, feature extraction, and Naïve Bayes — into one complete, realistic…
28. Unit 3 — Sentiment Analysis: Approaches & Techniques — Sentiment Analysis — Approaches & Techniques Sentiment analysis (opinion mining) determines the emotional tone/polarity of a piece of text — typically positive , negative , or…
29. Unit 3 — Sentiment Analysis: Hands-on with Python — Sentiment Analysis — Hands-on with Python Lexicon-Based Sentiment with VADER (Great for Social Media Text) VADER (Valence Aware Dictionary and sEntiment Reasoner) is a…
30. Unit 3 — Information Extraction — Information Extraction (IE) Information Extraction (IE) is the task of automatically pulling structured information (entities, relationships, facts) out of unstructured text . It…
31. Unit 3 — Introduction to Text Summarization — Introduction to Text Summarization Text summarization automatically condenses a document into a shorter version that preserves its most important information. There are two…
32. Unit 4 — Word Embeddings: Word2Vec — Word Embeddings — Word2Vec Recall from Unit 3 that Bag-of-Words / TF-IDF treats every word as an independent dimension — "good" and "great" share no similarity in that…
33. Unit 4 — Introduction to Deep Learning for NLP — Introduction to Deep Learning for NLP Classical NLP methods (n-gram LMs in Unit 2, Naïve Bayes with TF-IDF in Unit 3, Word2Vec in the previous lesson) hit fundamental limits:…
34. Unit 4 — Introduction to Transformers — Introduction to Transformers The Transformer architecture (Vaswani et al., "Attention Is All You Need", 2017) replaced RNNs/LSTMs (previous lesson) as the dominant architecture in…
35. Unit 4 — Large Language Models (LLMs) — Large Language Models (LLMs) Large Language Models (LLMs) are Transformer-based (previous lesson) language models (recall the definition from Unit 2) scaled up to billions or…
36. Unit 4 — NLP Applications: Sentiment Analysis, Machine Translation & Question Answering — NLP Applications — Sentiment Analysis, Machine Translation & Question Answering This lesson and the next survey how the concepts across all four units combine into the real-world…
37. Unit 4 — NLP Applications: Text Summarization, Chatbots & Speech Assistants — NLP Applications — Text Summarization, Chatbots & Speech Assistants Text Summarization — Modern Deployment Unit 3 introduced extractive (TF-IDF/TextRank) and abstractive…
38. Unit 4 — NLP Applications: Generative AI — NLP Applications — Generative AI Generative AI refers to systems that create new content — text, code, images, audio — rather than only classifying or extracting information from…
39. Previous Year Questions — Natural Language Processing — Previous Year Questions PYQ papers for this course will be added here soon. Check back later for: - End Term Examination papers - Mid Term papers -…

About This Course

Natural Language Processing — University Course

This course covers Natural Language Processing (NLP) as taught in undergraduate/postgraduate BCA/MCA/BTech university courses. The syllabus is divided into 4 units — introduction and text preprocessing, syntactic/semantic analysis with language models, feature extraction and text classification, and word embeddings with deep learning, transformers, and real-world applications.

Syllabus at a Glance:

What you will learn:

• How machines process, understand, and generate human language, and why it is a genuinely hard problem
• Every stage of a text preprocessing pipeline — tokenization through stop-word removal — with runnable Python code
• POS tagging, grammar-based parsing, named entity recognition, word sense disambiguation, and n-gram language models
• How to turn text into numeric features (BoW, TF-IDF) and classify/summarize/extract information from it
• Word embeddings (Word2Vec), the Transformer architecture, and how modern LLMs and generative AI applications are built on these foundations

PYQ papers are available at the end of the lesson list.

Continue reading: About This Course →

Frequently asked questions

Is the Natural Language Processing course really free?

Yes. The entire Natural Language Processing course on Siksha Sarovar is free to read with no account required. You can optionally sign in with Google to save your progress.

Do I get a certificate for Natural Language Processing?

Yes — finish the lessons and pass the quiz to earn a free, verifiable certificate you can share on LinkedIn or with recruiters.

Can I run code while learning?

Yes. The built-in online compiler runs C, C++, Python, Java, PHP, JavaScript, C# and SQL directly in your browser — no installation needed.