RTMNU · Final Year B.Tech Computer Science & Engineering · CBCS
Natural Language Processing
BTECHCSE703T · Elective V · Semester VII · 3 credits · College 30 + university 70
One of the Elective V options.
Unit 1: Introduction to NLP
8 hoursThe definition, scope, history and applications of natural language processing; its challenges and their solutions; basic concepts in linguistics and language processing; text preprocessing and normalisation.
Examined in the 70-mark end-semester paper
- Natural language processing and its challenges
- Stages of NLP
- Tokenisation, stemming and lemmatisation
- Morphological analysis and finite-state transducers
Unit 2: Language Models and Text Classification
7 hoursLanguage modelling with n-gram models; classifying and categorising text with naive Bayes, decision trees and support vector machines; evaluation measures for text classification.
Examined in the 70-mark end-semester paper
- N-gram language models and smoothing
- Evaluating language models
- Naive Bayes for text classification
- Support vector machines and kernels
- Confusion matrix, precision, recall and F1
Unit 3: Information Retrieval and Extraction
7 hoursVector space and probabilistic retrieval models, retrieving relevant documents with query expansion; named entity recognition, relation extraction and open information extraction.
Examined in the 70-mark end-semester paper
- Information retrieval with the vector space model
- Probabilistic retrieval and BM25
- Relevance feedback
- Named entity recognition
- Relation extraction
Unit 4: Syntactic and Semantic Analysis
7 hoursPart-of-speech tagging and parsing, dependency parsing; semantic analysis and sentiment analysis; word embeddings and semantic similarity.
Examined in the 70-mark end-semester paper
- Part-of-speech tagging
- Syntactic parsing and probabilistic CFGs
- Treebanks and universal dependencies
- Lexical semantics and WordNet
- Sentiment analysis
- Word embeddings: word2vec and doc2vec
Unit 5: Advanced Topics in NLP
7 hoursNeural-network and deep-learning models for NLP tasks, natural language generation, and dialogue systems and chatbots.
Examined in the 70-mark end-semester paper
- Attention mechanism
- Contextual embeddings and BERT
- Encoder–decoder sequence-to-sequence models
- Dialogue systems and natural language generation
Unit contents are summarised from the official RTMNU syllabus . AiCanCode.org is not affiliated with Rashtrasant Tukadoji Maharaj Nagpur University (RTMNU).