Department of Information Technology

Institute of Southern Punjab Multan

COURSE DESCRIPTION FORM

CS/IT

Discipline / Program

Course Description

1
 Department of Information Technology
Institute of Southern Punjab Multan
Course Code
Course Title Natural Language Processing
Credit Hours 3(3T+0L)
Prerequisites by Course(s) and
Topics
Assessment Instruments with Sessional (25%)
Weights (homework, quizzes,  Attendance 40%
midterms, final, programming  Assignments 20%
assignments, lab work, etc.)  Quizzes 20%
 Semester Project 20%
Mid Term (25%)
Final Term (50%)
Course Coordinator Miss Maryam Ismail
URL (if any)
Textbook 1. Python Machine Learning, Sebastian Raschka. Publisher: Packt
Publishing, 2015.
2. Natural Language Processing with Python: Analyzing Text with the
Natural Language Toolkit Latest Edition, Steven Bird, Ewan Klein
and Edward Loper Publisher: O'Reilly Media, 2009.
3. Speech and Language Processing, Latest Edition, Daniel Jurafsky
and James H. Martin Publisher: Prentice Hall, 2000.

Reference Material Notes / Slides / Websites / Any other Material given by Teacher
Course Objectives This course introduces the fundamental concepts and techniques of
natural language processing (NLP). Students will gain an in-depth
understanding of the computational properties of natural languages
and the commonly used algorithms for processing linguistic
information. The course examines NLP models and algorithms using
both the traditional symbolic and the more recent statistical
approaches.
Course Outcomes Upon successful completion of the course, the student will be able to:
 Identify techniques for information retrieval, language
translation, and text classification.
 List the advantages of using standard corpora. Identify
examples of current corpora for a variety of NLP tasks.
 Define and contrast deterministic and stochastic grammars,
providing examples to show the adequacy of each.
 Simulate, apply, or implement classic and stochastic
algorithms for parsing natural language

Course Contents (As per HEC)

Topics Covered in the Course, Topics Covered (16 Lectures Plan)
with Number of Lectures on Each
Topic
Week # 1 Deterministic grammars
 Overview
 Representation
 PDA
Stochastic grammars

2
 Department of Information Technology
Institute of Southern Punjab Multan
 Overview
 Representation
 Terminals
 Context Sensitivity
Week # 2 Parsing algorithms
 The CKY algorithm
 Viterbi CKY
 Parsing general CFGs
Week # 3 CFGs
 Definition
 Derivation
 Tree Derivation
Representing meaning / Semantics
 Meaning Representation
 Meaning Interpretation
Week # 4 Semantic roles
 Definition
 Agent
 Patient
 Theme
 Experiencer
Week # 5 Temporal representations
 Normalization
 Expression Extraction
 Ordering of Events
Week # 6 Corpus-based methods
 Accessing text corpus
 Conditional frequency distributions
Week # 7 N-grams
 Unigram
 Bigram
 Trigram
HMMs
Week # 8 Smoothing and backoff,
Week # 9 POS tagging
 Markov Model Taggers
 The Viterbi algorithm
 Trigram taggers
Morphology
 Rules
Week # 10 Information retrieval
 tf-idf
 Term Frequency
 Lemmatization
 Stemming
Week # 11 Vector space model
 Indexing
 Ranking
Week # 12 Precision and recall
 Confusion matrix
 True positive
 False positive
 True negative
3
 Department of Information Technology
Institute of Southern Punjab Multan
 False negative
Week # 13 Information extraction
 Architecture
 Chunking
 Developing and Evaluating Clunkers
Week # 14 Language translation

Week # 15 Text classification Categorization

 Decision tree
 Maximum entropy model
 k Nearest Neighbor Classification etc

Week# 16 Bag of words model

Practical Assignments Covered in As per LAB Schedule

the LAB Session

COURSE DESCRIPTION FORM

TO BE FILLED BY COORDINATORS & TEACHERS AT THE END OF SEMESTER

Laboratory
Projects/Experiments / Reports
Done in the Course
Programming Assignments Done
in the Course
Class Time Spent on (in credit Theory Problem Solution Social and Ethical
hours) Analysis Design Issues

Oral and Written Communications Every student is required to submit at least _____ written reports of
typically _____ pages and to make _____ oral presentations of
typically _____ minute’s duration. Include only material that is graded
for grammar, spelling, style, and so forth, as well as for technical
content, completeness, and accuracy.

CLOs Domain-BT
Course Learning Outcomes: Level
Identify
At the end of thistechniques for information
course, students retrieval,
will be able to: language C-1
CLO 1 translation, and text classification
List the advantages of using standard corpora. Identify C-2
CLO 2 examples of current corpora for a variety of NLP tasks
Define and contrast deterministic and stochastic grammars, providing C-3
CLO 3 examples to show the adequacy of each.
4 Simulate, apply, or implement classic and stochastic C-4
CLO 4 algorithms for parsing natural language
 Department of Information Technology
Institute of Southern Punjab Multan

* BT= Bloom’s Taxonomy, C=Cognitive domain, P=Psychomotor

domain, A= Affective domain
Mapping of CLOs to Program Learning Outcomes (PLOs):
CLO’s/PLO’s CLO1 CLO2 CLO3 CLO4
1: Academic Education ✓ ✓ ✓ ✓
2: Knowledge for Solving Computing Problems ✓ ✓ ✓ ✓
3:Problem Analysis ✓ ✓
4:Design / Development of Solutions ✓
5: Modern Tool Usage ✓
6: Individual & Team Work
7:Communication
8: Computing Professionalism and Society
9: Ethics
10: Life Long Learning
Learning Methodology:
✓ Lectures-combining facts, principles, concepts and generalizations
✓ Interactive learning activity
✓ Audio and visual aids (ppt slides etc)
✓ Employing humor related to concepts
✓ Providing motivational cues
✓ Emphasizing on important issues related to subject
✓ Reinforcing learning and clarifying misconceptions

Instructor Name Muhammad Kashif

Instructor Signature ____________________________
Date ______________________________