PARUL UNIVERSITY - Faculty of Engineering and
Technology
Department of Computer Science & Engineering
SYLLABUS FOR 7th Sem BTech PROGRAMME
Deep Learning with NLP
Type of Course: B.Tech
Prerequisite: Basics of Python & Machine Learning
Rationale: Natural language processing (NLP) is a crucial part of artificial intelligence (AI). This course
will introduce about the core concepts related to Natural Language Processing and its applications. A
broad introduction about incorporation of Deep Learning techniques in Natural Language Processing is
considered.
Teaching and Examination Scheme:
Teaching Scheme Examination Scheme
Credit External Internal Total
Lect Hrs/ Tut Hrs/ Lab Hrs/
T P T CE P
3 0 0 3 60 - 20 20 - 100
Lect - Lecture, Tut - Tutorial, Lab - Lab, T - Theory, P - Practical, CE - CE, T - Theory, P - Practical
Contents:
Teaching
Sr. Topic Weightage
Hrs.
Introduction to Natural Language Processing: The First Wave:
Rationalism, The Second Wave: Empiricism, The Third Wave: Deep
Learning, what makes Natural Language Processing Difficult? What do 15% 8
we want to achieve through Natural Language Processing? Common
1 Terms Associated with Language Processing, Introduction to basics of
NLP operations: Word Level Analysis, Syntactic Analysis, Semantic
Analysis, Word Sense Disambiguation, Discourse Processing, Part of
Speech (PoS) Tagging, Natural Language Inception, Information
Retrieval, Applications of NLP.
Introduction to Deep Learning: Introduction to the Deep Learning,
2 Basic Structure of Neural Network, Types of Activation Function, Types
of Neural Network: Feedforward Neural Network, Convolutional Neural 15% 8
Network, Recurrent Neural Network, Encoder Decoder Networks,
Recursive Neural Network, Multilayer Neural Network, Stochastic
Gradient Descent, Backpropagation Algorithm.
Word Vector Representations: Introduction to Word Embedding:
Neural Language Model, Word2Vec: Skip-Gram Model, Model
3 Components: Architecture, Hidden Layer, Output Layer, CBOW Model, 20% 10
Subsampling Frequent Words: Negative Sampling. Efficient Softmax
approximations, Sampling-based approximations for Softmax, Glove,
Cross-lingual word embedding models
Recurrent Neural Network for NLP: What is RNN? Recurrence,
Difference between Feedforward and Recurrent Neural Networks,
Basics of Recurrent Neural Networks, Natural Language Processing & 20% 8
4
Recurrent Neural Networks, RNN’s Mechanism, Training RNN, Meta
meaning of Hidden State of RNN. Tuning RNN, Long Short-Term
Memory Networks, Sequence to Sequence Models, Advance Sequence
to Sequence Models.
Chatbot Development: Introduction to the Chatbot, Origin of Chatbot,
How does a chatbot work? Why are chatbots such a big opportunity, 10% 4
5 Conversational bot, Chatbot: Automatic Text Generation procedure,
Introduction to ChatGPT AI Chatbot.
Deep Learning in Sentiment Analysis: Introduction, Sentiment-
Specific Word Embedding, Sentence Level Sentiment Classification:
6 Convolution Neural Network, Recurrent Neural Network, Recursive 20% 8
Neural Network, Integration of External Resources, Document Level
Sentiment Classification, Fine-Grained Sentiment Analysis, Opinion
Mining, Targeted Sentiment Analysis, Aspect Level Sentiment
Analysis, Stance Detection, Sarcasm Recognition
*Continuous Evaluation:
It consists of Assignments/Seminars/Presentations/Quizzes/Surprise Tests (Summative/MCQ) etc.
Reference Books:
1. Deep Learning for Natural Language Processing: Creating Neural Networks with Python: P. Goyal,
S. Pandey and K. Jain by Apress.
2. Deep Learning in Natural Language Processing: Li Deng, Yang Liu by Springer.
3. Natural Language Processing: Develop Deep Learning Models for Natural Language in Python by
Jason Brownlee
4. Handbook of Natural Language Processing: Nitin Indurkhya Fred J. Damerau, CRC Press.
Course Outcome:
After Learning the course, the students shall be able to:
1. Understand the concepts of Natural Language Processing.
2. Understand the concepts of Deep Learning
3. Apply several models of Deep Learning in Natural Language Processing
4. Analyze the importance of Recurrent Neural Network & LSTM in NLP.
5. Understand about recent developments in the field of Chatbots.
6. Classify and Implement Sentimental Analysis techniques.
