(Established under the Presidency University Act, 2013 of the Karnataka Act 41 of 2013)

[2024-25 EVEN SEMESTER]

COURSE PLAN [Revision 03–July 2023]

SCHOOL: PSCS DEPT: CSE DATE OF ISSUE: 09/01/2025

NAME OF THE PROGRAM: : Bachelor of Technology in Computer Engineering

P.R.C. APPROVAL REF.: : PU/AC-23.9/SOCSE04/COM/2022-26
SEMESTER/YEAR: : VI Sem/ III Year
COURSE TITLE & CODE: : Natural Language Processing & CSE3188
COURSE CREDIT : 2-0-2-3
STRUCTURE:
CONTACT HOURS: : 60 Hours
COURSE IC: : Dr. Sandeep Albert Mathias, Dr. Galiveeti Poornima
COURSE INSTRUCTOR: : Dr. Sandeep Albert Mathias, Dr. Galiveeti Poornima, Dr. Jacob Augustine, Dr. Swati
Sharma, Ms. Vineetha B, Ms. Riya Sanjesh
COURSE URL : [Link]

PROGRAM OUTCOMES:

PO 1: Engineering Knowledge: Apply the knowledge of mathematics, science, engineering fundamentals, and an engineering
specialization to the solution of complex engineering problems.

PO 2: Problem Analysis: Identify, formulate, research literature, and analyze complex engineering problems reaching substantiated
conclusions using first principles of mathematics, natural sciences, and engineering sciences.

PO 3: Design/development of Solutions: Design solutions for complex engineering problems and design system components or
processes that meet t h e specified needs with appropriate consideration for the public health and safety, and the cultural, societal, and
environmental considerations.

PO 4: Conduct Investigations of Complex Problems: Use research-based knowledge and research methods including design of
experiments, analysis and interpretation of data, and synthesis of the information to provide valid conclusions.

PO 5: Modern Tool usage: Create, select, and apply appropriate techniques, resources, and modern engineering and IT tools including
prediction and modelling to complex engineering activities with an understanding of the limitations.

PO 6: The Engineer and Society: Apply reasoning informed by the contextual knowledge to assess societal, health, safety, legal and
cultural issues and the consequent responsibilities relevant to the professional engineering practice.

PO 7: Environment and Sustainability: Understand the impact of the professional engineering solutions in societal and environmental
contexts, and demonstrate the knowledge of, and need for sustainable development.

PO 8: Ethics: Apply ethical principles and commit to professional ethics and responsibilities and norms of the engineering practice.

PO 9: Individual and Team Work: Function effectively as an individual, and as a member or leader in diverse teams, and in
multidisciplinary settings.
1
PO 10: Communication: Communicate effectively on complex engineering activities with the engineering community and with society
at large, such as, being able to comprehend and write effective reports and design documentation, make effective presentations, and give
and receive clear instructions.

PO 11: Project Management and Finance: Demonstrate knowledge and understanding of the engineering and management principles
and apply these to one’s own work, as a member and leader in a team, to manage projects and in multidisciplinary environments.

PO 12: Life-long Learning: Recognize the need for, and have the preparation and ability to engage in independent and life-long
learning in the broadest context of technological change.

PROGRAM SPECIFIC OUTCOMES :

On successful completion of the Program, the students shall be able to:

PSO 01: [Problem Analysis]: Identify, formulate, research literature, and analyze complex engineering problems related to Software
Engineering principles and practices, Programming and Computing technologies reaching substantiated conclusions using first principle

PSO 02: [Design/development of Solutions]: Design solutions for complex engineering problems related to Software Engineering
principles and practices, Programming and Computing technologies and design system components or processes that meet the specified
needs

PSO 03: [Modern Tool usage]: Create, select, and apply appropriate techniques, resources, and modern engineering and IT tools
including prediction and modelling to complex engineering activities related to Software Engineering principles and practices, program
solutions using the latest tools and techniques.

COURSE PREREQUISITES:

• CSE3001 – Artificial Intelligence and Machine Learning

COURSE DESCRIPTION:

This course introduces the basics of Natural Language Processing methods with specific emphasis on modern applications. The course
will teach students different concepts of natural language processing, such as word representations, text representations, part-of-speech
tagging, word sense disambiguation, parsing, etc.

Topics: Word representations, Part-of-Speech tagging, chunking, parsing, text classification, sentiment analysis, named entity
recognition, and machine translation.

COURSE OBJECTIVE:

The objective of the course is to familiarize the learners with the concepts of Natural Language Processing as mentioned above and
attain Skill Development through experiential Learning techniques

COURSE OUTCOMES:

On successful completion of the course the students shall be able to:

TABLE 1: COURSE OUTCOMES

CO Number CO Expected BLOOMS LEVEL
CO1 Define different problems related to natural language processing. Remember
CO2 Discuss using NLP techniques for different applications. Understand
CO3 Propose solutions for a particular NLP problem using different machine Apply
learning and deep learning techniques.
CO4 Use different NLP tools and packages. Apply

MAPPING OF C.O. WITH P.O.: [H-HIGH , M- MODERATE, L-LOW]

TABLE 2: CO PO Mapping ARTICULATION MATRIX

CO.
No PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO 10 PO11 PO 12

2
 CO1 M H H H H - - - - - - -

CO2 M H M H M - - - - - - -

CO3 M H M H H - - - - - - -

CO4 L L L L H - - - - - - -

TABLE 2b: CO PSO Mapping ARTICULATION MATRIX

CO No. PSO 1 PSO 2 PSO 3
CO1 H H H
CO 2 H H H
CO3 H H H
CO4 H H H

COURSE CONTENT (SYLLABUS):

Module 1: Introduction to Natural Language Processing [13 Sessions [L7 + P6]] [Blooms Level Selected: Apply]
Definition of Natural Language Processing; Description of various NLP tasks; Sentence and word boundary detection; Introduction to
word representation, PoS tagging, Chunking and Parsing, and text classification; Introduction to NLP applications like Sentiment
Analysis, Named Entity Recognition, and Machine Translation.

Module 2: Word and Text Representation [15 Sessions [L9 + P6]] [Blooms Level Selected: Apply]
Introduction to Word Embeddings; Creation of word embeddings using Skipgram; Using word embeddings like GloVe / fastText; Cross-
lingual word embeddings (Eg. MUSE); Pre-trained monolingual and multilingual language models. Text Representations Using BoW,
feature-based, Kernel, embedding-based representations.

Module 3: Part-of-Speech Tagging, Chunking and Parsing [15 Sessions [L7 + P8]] [Blooms Level Selected: Apply]
Sequence Labeling and Hidden Markov Model; Viterbi Algorithm; Part-of-Speech Tagging; Using NLTK and Spacy for PoS Tagging;
Building a PoS Tagger; Chunking and Constituency Parsing; Using Parser from NLTK.

Module 4: NLP Applications [13 Sessions [L5 + P8]] [Blooms Level Selected: Apply]
Lexical Resource Creation – Creation and evaluation of Lexical Resources. Agreement metrics. Sentiment Analysis – Definitions,
Challenges (Sarcasm, Thwarting, etc.). Named-Entity Recognition – Definition, Relationship between NER and PoS tagging. Machine
Translation – Definition, Challenges, Approaches and Paradigms, Evaluation Techniques.

SKILL SETS TO BE DEVELOPED:

Graduate of the [Link]. Program in Computer Science and Engineering shall be able to;
1. An attitude of enquiry.
2. Confidence and ability to tackle new problems.
3. Ability to interpret events and results.
4. Ability to work as a leader and as a member of a team.
5. Assess errors in systems/processes/programs/computations and eliminate them.
6. Observe and measure physical phenomena.
7. Write reports.
8. Select suitable equipment, instrument, materials & software
9. Locate faults in system/Processes/software.
10. Manipulative skills for setting and handling systems/Process/ Issues
11. The ability to follow standard /Legal procedures.
12. An awareness of the Professional Ethics.
13. Need to observe safety/General precautions.
14. To judge magnitudes/Results/issues without actual measurement/actual contacts

3
DELIVERY PROCEDURE (PEDAGOGY):

TABLE 3: SPECIAL DELIVERY METHOD/ PEDAGOGY PLANNED WITH TOPICS

Pedagogy title/ short ** At end of semester please
Lecture
S. No Subtopic as per lesson Plan explanation of adopted update whether activity was
Number
pedagogy done
1 L13 Feedforward Neural Network Mathematics Bee
2 L25 Lexical Resource Creation and Participative Learning
Evaluation

REFERENCE MATERIALS:

Text Book:

T1. Daniel Jurafsky, James H. Martin. “Speech and Language Processing: An Introduction to Natural Language Processing”,
Computational Linguistics and Speech, Pearson Publication, 2024 (3rd Edition Draft).

T2. Aditya Joshi, Pushpak Bhattacharyya. “Natural Language Processing”, Wiley Publication, 2023 (1st Edition).

References:

R1. Chris Manning and Hinrich Schütze. “Foundations of Statistical Natural Language Processing”, MIT Press. Cambridge, MA. 1999
(1st Edition)

Other E-Resources (NPTEL and other video links):

1. Pushpak Bhattacharyya (IIT Bombay), “Natural Language Processing”. Link: [Link]

2. Pawan Goyal (IIT Kharagpur), “Natural Language Processing”.
Link: [Link]
3. Ramaseshan R (Chennai Mathematical Institute), “Applied Natural Language Processing”.
Link: [Link]
4. Pawan Goyal (IIT Kharagpur), “Deep Learning for Natural Language Processing”. Link:
[Link]
5. Tanmoy Chakraborty (IITD) and Soumen Chakrabarti (IITB), “Introduction to Large Language Models (LLMs)”. Link:
[Link]

Websites:

W1. Website for T1 - [Link] - VERY VERY IMPORTANT!!!

SPECIFIC GUIDELINES TO STUDENTS

1. The assessment components are as follows:

a. End Term = 100 marks / 50% weightage
b. Mid Term = 50 marks / 25% weightage
c. CA = 50 marks / 25% weightage

2. The CA, Mid-Term, and End-Term will have half of their marks being linked to the lab / practicals. This means that the end
term will have 50 marks from lab-related stuff, the mid-term will have 25 marks from lab-related stuff and the CA will have
25 marks from lab related stuff.

3. With respect to the theory, there will be 4 module wise tests to be conducted after each Module. In addition to this, there will
also be weekly AQTs (a.k.a. Adversarial Quiz Tests). AQTs are exams which are held online, where your aim is to, not only
score marks by answering questions correctly, but to also convince other people to write incorrect / incomplete answers. Each
Module Test is worth 5 marks (so totally 20 marks)

4
 4. The remaining 5 marks will be in the form of a Course Assignment. The course assignment involves you solving weekly
NPTEL assignments from “Deep Learning for Natural Language Processing”. THERE WILL BE NO MAKE-UP FOR
THIS (which is why we will share a video of how to register). Please note that the NPTEL Assignments will end at 11:59 p.m.
on Wednesday Night every week.

5. The lab part of the CAs will be evaluated in the form of 8 LAB CAs which will be CENTRALLY EVALUATED. 4 Lab CAs
will be before the Mid-Term, and 4 will be after it. Each set of 4 Lab CAs will be evaluated for 10 marks each (so totally 20
marks). You must also write a lab record for the remaining 5 marks.

6. The mid-term and end-term will also have lab-related tasks. Details for the same will be disclosed closer to the actual
examination date.

7. PPTs will be shared ONLY ON COMPLETION of a Module. A module will be deemed completed only upon completion of
the test for that module.

8. Do not be disruptive in the classroom and labs. The more you learn in the class, the easier your examinations will be.

9. Take notes in class. They will be very useful for the module tests (where you can use your notes as it is open notes).

10. You need to maintain a minimum of 75% attendance. 25% of attendance is leeway that is granted for medical issues, important
personal duties, etc.

COURSE SCHEDULE:

TABLE 4: COURSE BROAD SCHEDULE

Sl. No. ACTIVITY PLANNED PLANNED TOTAL NUMBER

STARTING CONCLUDING OF PERIODS
DATE DATE
01 Over View of the course 20th January, 2025 20th January, 2025 1
02 Module 1 21st January, 2025 4th February, 2025 12
03 Continuous Assessment 4th February, 2025 4th February, 2025 1
Test for Module 1
04 Module 2 5th February, 2025 15th March, 2025 15
05 Continuous Assessment 15th March, 2025 15th March, 2025 1
Test for Module 2
06 Mid-Term Exams 17th March, 2025 21st March, 2025 4
07 Module 3 24th March, 2025 17th April, 2025 14
08 Continuous Assessment 17th April, 2025 17th April, 2025 1
Test for Module 3
09 Module 4 21st April, 2025 9th May, 2025 10
10 Continuous Assessment 9th May, 2025 9th May, 2025 1
Test for Module 4
11 Last Instruction Day 10th May, 2025 10th May, 2025 0
12 End Term Examination 26th May, 2025 6th June, 2025 N/A

Sl. Starting Concluding Total

Activity
No. Date Date Number
of Periods
01 File Handling Using Python 20th January, 2025 31st January, 2025 2
02 Introduction to NLP Tools 3rd February, 2025 7th February, 2025 2
03 Corpus Cleaning Techniques 10th February, 2025 14th February, 2025 2
04 Word Vector Usage 17th February, 2025 21st February, 2025 2

5
 05 Language Identification 24th February, 2025 7th March, 2025 4
06 Lexical Simplification 10th March, 2025 28th March, 2025 2+2
07 Mid-Term Examination 17th March, 2025 21st March, 2025 2
08 Sentiment Analysis 1st April, 2025 12th April, 2025 4
09 Named Entity Recognition 15th April, 2025 17th April, 2025 2
10 Hidden Markov Model 14th April, 2025 2nd May, 2025 4
11 Machine Translation 5th May, 2025 9th May, 2025 2

DETAILED SCHEDULE OF INSTRUCTION:

TABLE 5: DETAILED COURSE SCHEDULE / LESSON PLAN (THEORY)

LOL HOL
SUBTOPIC
(Lower (Higher CO Teaching
Session no TOPIC Reference
Order Order Number Pedagogies
LO: Students shall be able to
Learning) Learning)
Overview of the course & Program Classroom
L1 N/A N/A N/A CHO
Integration Lecture
Introduction to NLP. History of
T1, Pg 3 to 4
NLP. Various Tasks of NLP LOL1 Classroom
L2 CO1 T2, Pg 1 to
LO1: Define NLP tasks LOL1 Lecture
12
LO2: Outline the history of NLP
Introduction to Text Classification
LOL1 Classroom T1, Pg 58 to
L3 LO1: Define text classification CO1
LOL3 Lecture 59
LO2: Evaluate text classification
Module 01:
Introduction to Part-of-Speech
Introduction
Tagging
to Natural LOL1 Classroom T1, Pg 24 to
L4 LO1: Define PoS Tagging CO1
Language LOL1 Lecture 29
LO2: List out different parts of
Processing
speech.
Module 01:
Introduction to NER
Introduction
LO1: Define NER LOL1 Classroom
L5 to Natural CO1 P1
LO2: Explain the challenges of LOL2 Lecture
Language
NER.
Processing
Introduction to Machine
Translation
LO1: Describe the history of LOL1 Classroom
L6 CO1 P1
machine translation LOL2 Lecture
LO2: Explain some of the
challenges in Machine Translation.
Classroom
Course Integration & Module 1 PPTs, Class
L7 N/A N/A CO1 Lecture +
Test Notes, etc.
Written Test
Module 1 Completed
Introduction to Word Embeddings T1, Pg 103
LO1: Define word embeddings LOL1 Classroom to 104
L8 CO2
LO2: Describe relationships LOL2 Lecture T2, Pg 15 to
between words. 16
Computing Similarity CO2
T1, Pg 108
Module 02: LO1: Calculate the dot product LOL3 Classroom
L9 to 113
Word and LO2: Calculate the cosine LOL3 Lecture
T2, Pg 32
Text similarity
Representati TF-Idf CO2
ons LO1: Calculate the TF and IDF of a LOL3 Classroom T1, Pg 113
L10
word in a document LOL3 Lecture to 116
LO2: Calculate the TF-IDF vector
Word2Vec CO2
LOL2 Classroom T1, Pg 119
L11 LO1: Explain how to generate word
LOL3 Lecture to 130
vectors using word2vec
6
 LO2: Use skipgram with negative T2, Pg 32 to
sampling to find word embeddings 36
Logistic Regression CO2
LOL2 Classroom T1, Pg 79 to
L12 LO1: Describe Logistic Regression
LOL3 Lecture 100
LO2: Calculate the sigmoid value
Feedforward Neural Networks CO2
LO1: Describe neurons in neural Classroom
networks LOL2 Lecture, and T1, Pg 134
L13
LO2: Calculate weights for LOL3 Mathematics to 144
different functions using neural Bee
networks
CO2 P2
Contextual Representations
T1, Pg 211
LO1: Describe BERT LOL2 Classroom
L14 to 244
LO2: Describe the tasks BERT is LOL2 Lecture
T2, Pg 42 to
trained for
48
Cross-lingual Word Embeddings CO2
LO1: Describe cross-lingual word
P2
embeddings like MUSE LOL2 Classroom
L15 P3
LO2: Describe multilingual pre- LOL2 Lecture
P4
trained language models like XLM-
RoBERTa
Classroom
Course Integration & Module 2 PPTs, Class
L16 N/A N/A CO2 Lecture +
Test Notes, etc.
Written Test
Module 2 Completed
L17 MID- Mid-Term Exams N/A N/A CO2 Examination
TERM
L18 Mid-Term Exams N/A N/A CO2 Examination
EXAMS
Classroom Mid-Term
L19 Discussion of Mid-Term Solutions N/A N/A CO2
Lecture QP
Sequence Labeling
T1, Pg 160
LO1: Define the problem of
LOL1 Classroom to 161
L20 sequence labeling CO3
LOL2 Lecture T2, Pg 53 to
LO2: Describe how we label a
60
sequence
Hidden Markov Model
T1, Pg 161
LO1: Define the Markov
LOL1 Classroom to 163
L21 Assumption CO3
LOL2 Lecture T2, Pg 60 to
LO2: Describe the Hidden Markov
61
Module 3: Model
Part-of- Forward Probability
Speech LO1: Calculate the forward
T1, Pg 167
Tagging, probability using initial, emission
LOL3 Classroom to 174
L22 Chunking and transition probabilities. CO3
LOL3 Lecture T2, Pg 61 to
and Parsing LO2: Calculate the backward
62
probability using final, emission
and transition probabilities
Viterbi Algorithm
T1, Pg 167
LO1: Describe the Viterbi
LOL2 Classroom to 174
L23 Algorithm CO3
LOL3 Lecture T2, Pg 62 to
LO2: Calculate the complexity of
66
Viterbi Algorithm
Constituents and CFG, PCFG
LO1: Define constituents Classroom T1, Pg 357
L24 LOL1 HOL3 CO3
LO2: Produce a parse tree for a Lecture to 358
string using CFG

7
 Classroom
Course Integration & Module 3 PPTs, Class
L25 N/A N/A CO3 Lecture +
Test Notes, etc.
Written Test
Module 3 Completed
Lexical Resource Creation and
evaluation LOL1 Participative T2, Pg 365
L26 CO4
LO1: Define Kappa LOL3 Learning to 378
LO2: Calculate different Kappas
Sentiment Analysis
LO1: Define Sentiment Analysis LOL1 Classroom T2, Pg 365
L27 CO4
LO2: Define the challenges of LOL3 Lecture to 378
Sentiment Analysis
Module 4: Named Entity Recognition
NLP LO1: Describe NER LOL1 Classroom T2, Pg 365
L28 CO4
Applications LO2: Relate NER with PoS LOL2 Lecture to 378
Program Tagging
Integration Machine Translation and
Evaluation
LO1: Describe Machine LOL1 Classroom T2, Pg 365
L29 CO4
Translation LOL2 Lecture to 378
LO2: Explain the challenges of
machine translation.
Classroom
Program Integration for the course PPTs, Class
L30 N/A N/A N/A Lecture +
& Module 4 Test Notes, etc.
Written Test
Module 4 Completed

Topics relevant to “SKILL DEVELOPMENT”: Developing AI solutions for Skill Development through Experiential Learning
techniques. This is attained through the Lab Experiments as mentioned in the assessment component.

TABLE 5: DETAILED SCHEDULE OF INSTRUCTION/LESSON PLAN (LAB)

REVISED BLOOM’S
Topics & Learning Outcome
TAXONOMY No. of
LOL HOL Lab
Sl. No. Task No. Skills
(Lower (Higher Sessions
LO: Students shall be able to
Order Order Needed
Learning) Learning)
P1 File Handling
LOL1 SK1 – SK8,
1 LO1: Read text files using Python N/A 1
LOL3 SK14
LO2: Parse text files using Python
P2 Introduction to NLP Tools
LOL3 SK1 – SK8,
2 LO1: Installing and using NLTK. N/A 1
LOL3 SK14
LO2: Installing and using Spacy.
P3 Corpus Cleaning Techniques
LO1: Using NLTK for CC
LOL3 SK1 – SK8,
3 techniques. N/A 1
LOL3 SK14
LO2: Preparing data for
downstream NLP Tasks
P4 Word Vector Usage
LO1: Download and use word
vectors. LOL3 SK1 – SK8,
3 N/A 1
LO2: Compute the similarity LOL3 SK14
between 2 words, find most similar
word and complete analogies
P5 & P6 Language Identification
LOL3 SK1 – SK8,
5 LO1: Build a language identifier N/A 2
LOL3 SK14
using BoW features

8
 LO2: Predict the language based
on the input text.
P7 & P9 Lexical Simplification
LO1: Implement a lexical
simplifier LOL3 SK1 – SK8,
6 N/A 2
LO2: Generate a simpler word LOL3 SK14
from the given input word and
sentence
P8 LOL1,
7 MID-TERM EXAMINATION LOL2, N/A 2 N/A
LOL3
P10 & P11 Sentiment Analysis
LO1: Implement a Sentiment
LOL3 SK1 – SK8,
8 Classifier N/A 2
LOL3 SK14
LO2: Compare an existing
sentiment classifier
P12 NER
LO1: Extract named entities using
LOL3 SK1 – SK8,
9 NLTK N/A 1
LOL3 SK14
LO2: Extract named entities using
Spacy.
P13 Implement a Hidden Markov
Model
LOL3 SK1 – SK8,
10 LO1: Implement a generic HMM N/A 2
LOL3 SK14
LO2: Calculate the forward
probability of the sequence
P14 Linguistic HMM
LO1: Develop a HMM for
LOL3 SK1 – SK8,
11 generalized NLP tasks N/A 1
LOL3 SK14
LO2: Evaluate it on a specific NLP
task.
P15 Machine Translation
LO1: Implement Machine
Translation from Huggingface LOL3 SK1 – SK8,
12 N/A 1
LO2: Evaluate quality of LOL3 SK14
Huggingface MT via Round-Trip
Translation

SKILL SETS:

Graduate of the B. Tech Program in Computer Science & Engineering shall be able to:

1. An attitude of enquiry.
2. Confidence and ability to tackle new problems.
3. Ability to interpret events and results.
4. Ability to work as a leader and as a member of a team.
5. Assess errors in systems/processes/programs/computations and eliminate them.
6. Observe and measure physical phenomena.
7. Write reports.
8. Select suitable equipment, instrument, materials & software
9. Locate faults in system/Processes/software.
10. Manipulative skills for setting and handling systems/Process/ Issues
11. The ability to follow standard /legal procedures.
12. An awareness of the Professional Ethics.
9
 13. Need to observe safety/General precautions.
14. To judge magnitudes/Results/issues without actual measurement/actual contacts

ASSESSMENT SCHEDULE:

TABLE 6: ASSESSMENT SCHEDULE

Course Venue,
Si. Duration in
Assessment type Contents outcome Marks Weightage Date and
No Hours
Number Time

Classroom,
Continuous Assessment CO1, CO2, 7th
1 Module 1 1 Hour 5 2.5%
Test for Module 1 (Theory) CO3 February,
2025
Classroom,
Continuous Assessment CO1, CO2,
2 Module 2 1 Hour 5 2.5% 14th March,
Test for Module 2 (Theory) CO3
2025
Labs, 14th
First Half of
3 Pre-Mid Term Labs (LAB) Module 1, Module 2 CO4 10 5% March,
Semester
2025
Exam Hall,
Mid-Term Exam CO1, CO2,
4 Module 1, Module 2 1.5 Hours 50 25% 21st March,
(Theory+LAB) CO3, CO4
2025
Classroom,
Continuous Assessment CO1, CO2,
5 Module 3 1 Hour 5 2.5% 17th April,
Test for Module 3 (Theory) CO3
2025
Online,
Course Assignment – Module 1, Module 2, CO1, CO2,
6 Full Semester 5 2.5% 25th April,
NPTEL (Theory) Module 3, Module 4 CO3
2025
Classroom,
Continuous Assessment CO1, CO2,
7 Module 4 1 Hour 5 2.5% 9th May,
Test for Module 4 (Theory) CO3
2025
Second Half Labs, 9th
8 Post-Mid Term Labs (LAB) Module 3, Module 4 CO4 10 5%
of Semester May, 2025
Module 1, Module 2, Labs, 9th
9 Lab Record (LAB) CO4 Full Semester 5 2.5%
Module 3, Module 4 May, 2025
Exam Hall,
End-Term Examination Module 1, Module 2, CO1, CO2,
10 3 Hours 100 50% 6th June,
(THEORY+LAB) Module 3, Module 4 CO3, CO4
2025

COURSE CLEARANCE CRITERIA: “AS PER ACADEMIC REGULATIONS OF THE UNIVERSITY”

MAKEUP EXAM POLICY:

“AS PER ACADEMIC REGULATIONS OF THE UNIVERSITY”

CONTACT TIMINGS IN THE CHAMBER FOR ANY DISCUSSIONS:

Students are encouraged to come for any discussions on this course during your Library Hrs.

SAMPLE THOUGHT PROVOKING QUESTIONS:

TABLE 7: SAMPLE THOUGHT PROVOKING QUESTIONS

SL QUESTION MARKS CO NO. BLOOM’S
NO LEVEL

10
 Explain how you can construct a title-case converter,
1 given that you have a set of titles but NO part-of- 10 CO3 Understand
speech tagger and NO part-of-speech tagged corpus.
Explain some of the challenges encountered in
2 machine translation and how you would resolve 10 CO4 Understand
them.
3 “Detecting sarcasm is very easy ” Explain 10 CO1 Understand
whether or not this statement is sarcastic and why.
Give an example of monolingual machine
4 translation. Discuss the challenges involved in the 10 CO4 Understand
chosen example.
One of the techniques for substituting words is by
using other words with a very high similarity.
5 However, this leads to a problem because antonyms 10 CO2 Understand
(words which are opposite in meaning for the target
word) possess a very high similarity with the target
word. Explain how you resolve this problem.

TARGET SET FOR COURSE OUTCOME ATTAINMENT:

TABLE 8: TARGET SET FOR ATTAINMENT OF EACH CO and ATTAINMENT ANALYSIS AFTER RESULTS

[Link] C.O. Course Outcomes Threshold Target set for Actual C.O. Remarks on attainment
No. Set for the attainment in Attainment in &Measures to enhance the
CO percentage Percentage * attainment *
01 CO1 Define different problems 65 65
related to natural language
processing.
02 CO2 Discuss using NLP 60 60
techniques for different
applications.
03 CO3 Propose solutions for a 50 50
particular NLP problem
using different machine
learning and deep learning
techniques.
04 CO4 Use different NLP tools and 70 70
packages.

Signature of the course Instructor In-Charge (s)

APPROVAL:
This course has been duly verified Approved by the D.A.C.

Signature of the Chairperson D.A.C.

Course Plan Verified by:

Master IC Name, Signature & Date:

11
Name and signature of the Instructor In-Charge (s) AFTER completing entries in Table number 3 and 8 at end of semester:

Name and signature of the DAC Chairperson AFTER completing entries in Table number 3 and 8 at end of semester:

12
BLOOM'S TAXONOMY SAMPLE VERBS

Learning Outcomes Verbs at Each Bloom Taxonomy Level to be used for writing the course Outcomes.

13