Natural Language Processing
Get the full GTU study material, English & Gujarati textbook PDFs, syllabus curriculum, and solved previous year question papers.
English Book & Chapters
English Book Coming Soon
We are working hard to add this material. Stay tuned for updates!
Follow on Instagram for UpdatesGTU Previous Year Papers
Natural Language Processing Syllabus — Unit-wise Content
The official GTU curriculum for Natural Language Processing (subject code 3174602) as prescribed for CS-DS · Semester 7 divides the course into 6 units, covering 35 listed topics. The unit-wise breakdown below is read from the GTU syllabus document for this subject code, so you can check what the course actually covers before deciding which papers to attempt.
Download the official syllabus PDF (3174602)Unit 1 Introduction to NLP
- Disadvantages of NLP, Components of NLP, Applications of NLP, How to build an NLP pipeline? Phases of NLP, NLP APIs
- NLP Libraries
- Empirical Laws: Zipf’s law, Heaps law
Unit 2 Text Processing
- Text Processing Basics
- Preprocessing: Lower case conversion
- Stop words removal
- Punctuation and digits removal
- Stemming and lemmatization
- Vector Space Models
- Statistical Properties of words 4 2 Language Modeling and Part of SpeechTagging: Unigram Language Model
- Advanced smoothing for language modeling
- Empirical Comparison of Smoothing Techniques
- Applications of Language Modeling
- NamedEntity Recognition
Unit 3 Words and Word Forms
- Embeddingrepresentationsforwords Lexical Semantics
- Word Sense Disambiguation
- Knowledge-Based and Supervised Word Sense Disambiguation 8 Program Name: Bachelor of Engineering Level : UG Subject Code: 3174602 Branch: Computer Science and Engineering (Data Science) Semester: VII Subject Name: Natural Language Processing
Unit 4 Text Analysis, Summarization and Extraction
- Sentiment Mining
- Text Classification
- Text Summarization
- Information Extraction
- Relation Extraction
- Cross- LingualIR
Unit 5 Machine Translation
- Need of MT, Problems of Machine Translation
- MT Approaches
- Direct Machine Translations
- Rule-Based Machine Translation
- Knowledge-Based MT System
- Statistical Machine Translation(SMT)
- Parameter learning in SMT (IBM models) using EM)
- Encoder-decoder architecture Neural Machine Translation
Unit 6 Topic Models
- Introduction to topic models
- Latent Semantic Analysis (LSA)
- Latent Dirichlet Allocation (LDA)
- Gibbs sampling for LDA
Study on Android App:
