CSIS3400 070CourseOutline 2024fall
CSIS3400 070CourseOutline 2024fall
PREREQUISITES
• Min grade C in CSIS 1175
• Students are expected to have mastered the knowledge in the prerequisites courses.
Text: Sowmya Vajjala, Bodhisattwa Majumder, Anuj Gupta and Harshit Surana, Practical
Natural Language Processing: A Comprehensive Guide to Building Real-World NLP
Systems, 2020, ISBN 1492054054.
Steven Bird, Ewan Klein, and Edward Loper, Natural Language Processing with
Python – Analyzing Text with the Natural Language Toolkit, 2020,
https://www.nltk.org/book/
1. Demonstrate different NLP concepts like corpora, tokens, N-grams, grammar, etc.
2. Model different forms of NLP data using appropriate representation methods.
3. Apply suitable methods to solve different NLP problems including Part-of-speech (POS)
tagging, chunking, Named-Entity recognition (NER), text categorization, etc.
4. Create a program for solving a particular NLP task.
5. Evaluate different NLP systems with appropriate metrics.
6. Apply deep learning methods to train NLP models.
7. Create NLP-related applications such as chatbot, sentiment analysis, recommender
systems, etc.
METHODS OF INSTRUCTION:
Lecture, Lab, Seminar
MEANS OF ASSESSMENT:
Lab 10%
Projects 15%
Quizzes 10%
Midterm 30%
Final 35%
TOTAL 100%
Notes:
• If you miss more than 30% of the scheduled classes, you will receive UN Grade for your course
grade.
• In order to pass the course, students must, in addition to receiving an overall course grade of
50%, also achieve a grade of at least 50% on the combined weighted examination components
(including quizzes, tests, exams).
• To receive a non-zero grade in the course, a student must attempt and hand in for marking at
least 70% of the assignments, examinations and quizzes. Work not handed in, or handed in too
late for marking, will automatically receive a zero.
• You must take the FINAL EXAM in order to get a grade; OTHERWISE you will receive an
automatic “UN” grade for the course. Please do not make any travel arrangement until you have
found out the exam dates and are sure that you do not have any time conflict with the exams.
• The student’s achievement will be converted to a letter grade, in accordance with department
policy.
MISSED TESTS OR FINAL EXAMINATION: Student will receive a zero mark for any missed test(s).
Exceptions may be considered in cases of extraordinary circumstances such as accidents, deaths in
the family, family emergencies’ including sick children. It is the responsibility of the student to inform
the College and/or the instructor at the earliest reasonable opportunity. Notification of the possibility of
missing the test or exam must be done prior to the test or exam date/time and based on the
instructor's preference might require supportive documentation where applicable.
TIMELINESS: Students are expected to be in class at the start of class. Any late student should enter
the session and try to not interrupt the flow of class activity as per Douglas College Student Conduct
policy.
STUDENT EFFORT: In addition to the scheduled times for classes and labs, students are expected
to spend at least six hours a week on this course. If you are consistently spending more time
than this, consider speaking with your instructor or reaching out to the Accessibility Centre for
assistance.
This following schedule is tentative and subject to change, as per the College policy.
Please do not make any travel arrangements during the final examination period – final exam
scheduling is beyond the instructor’s control. Please see the Registrar’s office immediately with any
conflict(s).
READINGS &
WEEK # DATES WEEKLY TOPICS ASSIGNMENT
DUE DATES
Course Introduction
Week 01 Sep 07 1
NLP Overview
4
Week 05 Oct 05 Text Classification 1
Quiz #1 (5%)
4
Week 06 Oct 12 Text Classification 2
Lab #1 (5%)
7
Week 10 Nov 09 Other Typical NLP Applications
Project #2 (5%)
8
Week 11 Nov 16 NLP in Social Media
Quiz #2 (5%)
9
Week 12 Nov 23 NLP in E-commerce
Lab #2 (5%)
!!!*** WISH YOU ALL THE VERY BEST FOR THIS COURSE ***!!!