Course File Format (1)
Course File Format (1)
Course Details
Name of the Programme: : Bachelor of Technology
Branch : CS AIML
Faculty Details
Name of Faculty Designation Department
8. List of students y
academic excellence.
M2: To develop technocrats with creative skills and leadership qualities, to solve local
M3: To impart human values and ethics in students, to make them socially and Eco-
friendly responsible.
Session: 2024-25
Department Vision and Mission
Semester: 7th
“To produce globally competent professionals having social values and committed to
serve the global needs with ability to work in an interdisciplinary environment”.
M3: To strive for continual enhancement of technical knowledge & innovation through
PEO1: Students must be able to apply software engineering principles to analyze complex computing
problems and identify their solutions.
PEO2: Students must be able to analyze, design, and implement the latest technology-driven projects.
PEO3: Students must be able to work in a collaborative environment and understand the ethical,
social, and economic impact of their work.
Session: 2024-25
Program Outcomes (POs)
Semester: 7th
PSO 1: Able to design and implement the data structures and algorithms to deliver
quality software products.
PSO 2: Able to apply Artificial Intelligence and Machine Learning concepts to solve
society-related needs.
Session: 2024-25
Institute Academic Calendar
Semester:7th
Session: 2024-25
Department Academic Calendar
Semester:7th
Session: 2024-25
Class Time Table & Personal Time Table
Semester:7th
- - - - - - - -
L_NLP
Monday
(CS)
L_NLP
Tuesday
(CS)
Wednesda L_NLP
LUNCH
y (CS)
L_NLP
Thursday
(CS)
L_NLP
Friday
(CS)
Saturday * The Time table for Saturday is similar as on Monday(only for 5th Saturday if applicable)
Subject
S.No Subject Name Faculty Name
Code
KCS-072 Natural Language Processing Mr.Chinmay Shukla(CS)
1
Semester:7th
Natural
1 KCS072 Language 3 0 0 30 20 50 100 150 3
Processing
(ii) Pre-requisites:
The prerequisites for this course are:
● Basic knowledge of formal-language/automata theory (i.e., regular and context-free grammars)
● Artificial intelligence (i.e., search, logic, and knowledge representation)
● Python Programming.
● Knowledge of machine learning
(iii) Course Objectives:
To introduce the fundamental concept and techniques of Natural Language Processing
To be able to map the appropriate techniques with the problem and solve real world problems.
(iv) Course Outcomes:
Bloom's
S.No Course Outcomes: Level
1 KCS072.1 To learn the fundamentals of natural language processing K2
2 KCS072.2 To understand the use of CFG and PCFG in NLP K2
3 KCS072.3 To understand the role of semantics of sentences and pragmatic K2
4 KCS072.4 To Introduce Speech Production And Related Parameters Of Speech. K2
To Show The Computation And Use Of Techniques Such As Short
5 KCS072.5 Time Fourier Transform, Linear Predictive Coefficients And Other K4
Coefficients In The Analysis Of Speech.
Course module contents Session: 2024-25
Semester:7th
(v) Syllabus:
I INTRODUCTION: Origins and challenges of NLP – Language Modeling:
Grammar-based LM, Statistical LM – Regular Expressions, Finite-State Automata –
English Morphology, Transducers for lexicon and rules, Tokenization, Detecting
and Correcting Spelling Errors, Minimum Edit Distance WORD LEVEL
ANALYSIS : Unsmoothed N-grams, Evaluating N-grams, Smoothing, Interpolation
and Backoff – Word Classes, Part-of-Speech Tagging, Rule-based, Stochastic and
Transformation-based tagging, Issues in PoS tagging – Hidden Markov and
Maximum Entropy models.
II SYNTACTIC ANALYSIS: Context Free Grammars, Grammar rules for English,
Treebanks, Normal Forms for grammar – Dependency Grammar – Syntactic
Parsing, Ambiguity, Dynamic Programming parsing – Shallow parsing –
Probabilistic CFG, Probabilistic CYK, Probabilistic Lexicalized CFGs – Feature
structures, Unification of feature structures.
III SEMANTICS AND PRAGMATICS:Requirements for representation, First-Order
Logic, Description Logics – Syntax-Driven Semantic analysis, Semantic
attachments – Word Senses, Relations between Senses, Thematic Roles, selectional
restrictions – Word Sense Disambiguation, WSD using Supervised, Dictionary &
Thesaurus, Bootstrapping methods – Word Similarity using Thesaurus and
Distributional methods.
IV BASIC CONCEPTS of Speech Processing : Speech Fundamentals: Articulatory
Phonetics – Production And Classification Of Speech Sounds; Acoustic Phonetics –
Acoustics Of Speech Production; Review Of Digital Signal Processing Concepts;
Short-Time Fourier Transform, FilterBank And LPC Methods.
V SPEECH-ANALYSIS: Features, Feature Extraction And Pattern Comparison
Techniques: Speech
Distortion Measures– Mathematical And Perceptual – Log–Spectral Distance,
Cepstral Distances,
Weighted Cepstral Distances And Filtering, Likelihood Distortions, Spectral
Distortion Using A
Warped Frequency Scale, LPC, PLP And MFCC Coefficients, Time Alignment And
Normalization
– Dynamic Time Warping, Multiple Time – Alignment Paths.
SPEECH MODELING : Hidden Markov Models: Markov Processes, HMMs –
Evaluation,
Optimal State Sequence – Viterbi Search, Baum-Welch Parameter Re-Estimation,
Implementation
Issues.
Semester:7th
(vi) Text books & Reference book:
1. Daniel Jurafsky, James H. Martin―Speech and Language Processing: An Introduction to Natural
Language Processing, Computational Linguistics and Speech, Pearson Publication, 2014.
2. Steven Bird, Ewan Klein and Edward Loper, ―Natural Language Processing with Python, First
Edition, OReilly Media, 2009.
3. Lawrence Rabiner And Biing-Hwang Juang, “Fundamentals Of Speech Recognition”, Pearson
Education, 2003.
4. Daniel Jurafsky And James H Martin, “Speech And Language Processing – An Introduction To
Natural Language Processing, Computational Linguistics, And Speech Recognition”, Pearson
Education, 2002.
5. Frederick Jelinek, “Statistical Methods Of Speech Recognition”, MIT Press, 1997.
6. 1. Breck Baldwin, ―Language Processing with Java and LingPipe Cookbook, Atlantic Publisher,
2015.
7. Richard M Reese, ―Natural Language Processing with Java, OReilly Media, 2015.
8. Nitin Indurkhya and Fred J. Damerau, ―Handbook of Natural Language Processing, Second Edition,
Chapman and Hall/CRC Press, 2010.
9. Tanveer Siddiqui, U.S. Tiwary, ―Natural Language Processing and Information Retrieval, Oxford
University Press, 2008
Mapping of Course Outcomes (COs)with Session: 2024-25
Program Outcomes (POs) and Program
Specific Outcomes (PSOs) Semester:7th
CO:
1 To learn the fundamentals of natural language processing
2 To understand the use of CFG and PCFG in NLP
3 To understand the role of semantics of sentences and pragmatic
4 To Introduce Speech Production And Related Parameters Of Speech.
To Show The Computation And Use Of Techniques Such As Short Time Fourier Transform,
5 Linear Predictive Coefficients And Other Coefficients In The Analysis Of Speech.
CO - PO - PSO Mapping
PROGRAM OUTCOMES(POs) & PROGRAM SPECIFIC OUTCOME(PSO)
C COs PO PO PO PO PO PO PO PO PO PO1 PO1 PO1 PSO PSO
O
1 2 3 4 5 6 7 8 9 0 1 2 1 2
UR
SE CO1 3 1 - - - - - - - - - 2 - 2
O
UT CO2 2 2 - - 1 - - - - - - 2 - 1
C
CO3 2 2 - - 1 - - - - - - 2 - 2
O
M 2 - 3 - 1 - - - - - - - 2
CO4
E
CO5 2 - - 1 - - - - - - - - 2
Mapping is as follows: 1 Slight (Low), 2 Moderate (Medium), 3 Substantial (High), ’-' denotes no correlation between
Session: 2024-25
Course coverage plan
Semester:7th
UNIT 1:
1.
INTRODUCTION: 1 18 & 19/9/24 18/09/24 T1
Origins and
challenges of NLP -
Language Modeling:
Grammar-based LM.
2.
Statistical LM-Regular 1 20/9/24 19/09/24 T1
Expressions, Finite-
State Automata -
English Morphology.
3.
Transducers for lexicon 1 23/9/24 20/09/24 T1
and rules,
Tokenization,
4.
Detecting and 1 24/09/24 23/09/24 T2
Correcting Spelling
Errors,
5.
Minimum Edit 1 25/09/24 24/09/24 T2
Distance
6.
WORD LEVEL 1 27/09/24 25/09/24 T1
ANALYSIS:
Unsmoothed N-grams,
7.
Evaluating N-grams. 1 27/09/24 27/09/24 T1
Smoothing
Interpolation and
Backoff Word Classes,
Part-of-Speech
Tagging,
8.
Rule-based, Stochastic 1 30/09/24 30/09/24 T2
and Transformation-
based tagging. Issues in
PoS tagging
9.
Hidden Markov and 1 01/10/24 1/10/24 T2
Maximum Entropy
models.
UNIT 2:
Dynamic
Programming parsing
Shallow parsing
1 04/10/24 03/10/24 T1
12. Probabilistic CFG.
Probabilistic CYK,
Probabilistic
13. Lexicalized CFGS-
1 07/10/2024 04/10/24 T2
Feature structures,
Unification of feature
structures.
14. 1 07/10/2024 07/10/24 T2
UNIT 3:
BASIC CONCEPTS
25 of Speech Processing: 21/10/24
Speech.
1 23/10/24 T1
UNIT 5: