EMA EMITS Undergraduate

COLLEGE PHILIPPINES
Del Pilar St., Pinamalayan, Or. TEACHING LEARNING
Mindoro PLAN
First Semester/A.Y. 2022-
I. COURSE TITLE: Natural Language Processing
II. COURSE CODE: CS NLP
CREDITS: Three (3) units
NUMBER OF HOURS: 3 hours/week
CLASS SCHEDULE: WThF 4:00-5:00 pm

III. COURSE DESCRIPTION

The intent of the course is to present a fairly broad graduate-level introduction to Natural Language Processing (NLP, a.k.a. computational
linguistics), the study of computing systems that can process, understand, or communicate in human language. The primary focus of the course will be on
understanding various NLP tasks as listed on the course syllabus, algorithms for effectively solving these problems, and methods for evaluating their
performance. There will be a focus on statistical and neural-network learning algorithms that train on (annotated) text corpora to automatically acquire the
knowledge needed to perform the task. Class lectures will discuss general issues as well as present abstract algorithms. Implemented versions of some of the
algorithms will be provided in order to give a feel for how the systems discussed in class "really work" and allow for extensions and experimentation as part
of the course projects.

IV. COURSE INTENDED LEARNING OUTCOMES

At the end of this course the students should be able to:

1. Explain the basics of linguistics and how they apply to NLP

2. Identify and explain the different components of an NLP system
3. Discuss the different steps involved in preprocessing and cleaning text data for NLP
4. Apply part-of-speech tagging and named entity recognition to a given text
 5. Explain the concept of stemming and lemmatization and how they can be used in NLP
6. Perform sentiment analysis on a given text
7. Discuss the basics of machine translation and its applications
8. Evaluate the performance of an NLP model

V. COURSE OUTLINE AND TIMEFRAME

Course Content/Subject Matter

Week 1-4 Introduction to Natural Language Processing (NLP)
Week 5 Preliminary Examination
Week 6-9 Text Preprocessing, Text Classification and Sentiment Analysis
Week 10 Midterm Examination
Week 11-13 Language Modeling, and Machine Translation
Week 14 Pre-final examination
Week 15-17 Natural Language Generation, and Advance Topics in NLP
Week 18 Final Examination

VI. COURSE CONTENT

Learning Experiences
Intended Learning Teaching and
Content Standard Time Assessment Task (ATs) References
Outcome Topic(s) Learning Activities
Frame
(TLAs)
Week 1-4
Demonstrate 4 weeks  Lecture-Discussion  Written quizzes Bird, S. et al.
At the end of the unit, the  INTRODUCTION TO
knowledge of the role (2009). Natural
students must have: NATURAL LANGUAGE
of natural language Language
1. Explained the common PROCESSING (NLP)
processing in  Syntax Analysis Processing with
use cases and  History of NLP
linguistics and and Morphology Python. O’Reilly
applications of NLP  Applications of NLP
computer science Practice Media, Inc.
2. Discussed the structure  Basics of linguistics
and properties of natural and how it applies to
Demonstrate languages and their NLP
competencies in representation in  Different components
determining the computational models of an NLP system
challenges and 3. Identified the major  Challenges and
limitations of natural challenges and limitations of working
language processing, techniques in NLP with natural language
and the limitations of data
current computational
models
Week 5 Examination
Week 6-9
Demonstrate 4 weeks  Lecture-Discussion  Hands-on Bird, S. et al.
At the end of the unit, the  TEXT PREPROCESSING,
knowledge of the Exercises (2009). Natural
students must have: TEXT CLASSIFICATION
principles and Language
AND SENTIMENT
techniques involved 1. Evaluated the  Preprocessing Processing with
ANALYSIS
in preparing text data effectiveness of Exercise and  Dataset Analysis Python. O’Reilly
for further processing different  Tokenization Vectorization Media, Inc.
or analysis. preprocessing Practice
 Stemming and
techniques, and lemmatization  Pencil and paper
selected the most
Demonstrate  Part-of-speech tagging test
appropriate ones for
competencies in  Sentiment Lexicon
a given task.  Named entity
selecting the Exploration
2. Selected the recognition
appropriate
appropriate  Text normalization
preprocessing steps
classification
for a given piece of  Supervised learning
method for a given
text, based on the algorithms for text
piece of text, based
specific requirements classification
on the specific
of the task or
requirements of the  Evaluating
application
task classification models
3. Evaluated the  Sentiment analysis
Demonstrate effectiveness of using lexicons
knowledge of the different sentiment
principles and analysis methods,
techniques involved and selected the
in classifying text most appropriate
data. ones for a given task

Demonstrate
proficiency in using
sentiment analysis
techniques to extract
valuable insights
from large collections
of text data

Week 10 Examination
Week 11-13
Demonstrate 3 weeks  Discussion  Laboratory Bird, S. et al.
At the end of the unit, the  LANGUAGE
knowledge of the  Language Model (2009). Natural
students must have: MODELING, AND
underlying principles Evaluation and Language
MACHINE
of natural language 1. Investigated the  Language Machine Processing with
TRANSLATION
and the ways in ethical and social Model Translation Python. O’Reilly
which language is implications of  n-gram models Exploration Evaluation Media, Inc.
used and understood language modeling  Smoothing techniques
by humans and natural language
processing, such as  Evaluation of language
issues related to models
Demonstrate bias, privacy, and  Rule-based machine
understanding of the potential impact translation
challenges and of these
limitations of technologies on  Evaluation of machine
machine translation society. translation
2. Discussed the basic
Demonstrate principles of
knowledge of the machine translation,
various techniques such as the use of
and approaches used algorithms and
in machine translation statistical models to
Demonstrate translate text from
competencies in one language to
creating a program another
that has nested
control structures
Week 14 Examination
Week 15-17
 NATURAL 3 weeks  Lecture-Discussion  Written quizzes Bird, S. et al.
At the end of the unit, the
LANGUAGE (2009). Natural
students must have:
GENERATION, AND Language
Demonstrate 1. Generated text from ADVANCE TOPICS  Text Generation  NLG Model Processing with
familiarity with the structured data using IN NLP and Natural evaluation Python. O’Reilly
role of natural various techniques, Language Media, Inc.
language generation  Text summarization Generation (NLG)
including template-
in generating human- based generation  Dialogue systems Model Exploration  Practical
like text and statistical examination
 Content planning and
generation realization
Demonstrate  Topic modeling
knowledge of the role 2. Evaluated and
of natural language  Information extraction
compared natural
generation and language generation  Discourse analysis
dialogue systems in and dialogue
applications such as systems using
virtual assistants and appropriate metrics
chatbots

3. Discussed the role

Demonstrate of natural language
competencies in processing in
making user-defined, applications such as
value-returning language translation
functions and summarization

Week 18 Examination
VII. COURSE REQUIREMENTS

1. Marked assignments
2. Collections of exercises
3. Major Exams

VIII. GRADING SYSTEM

Major Exam 40%

Class Standing 30%
Project 20%
Attendance 5%
Behavior 5%
Total 100%

IX. CLASSROOM POLICIES

1. Attendance is checked regularly. Late comers will not be admitted after 15 minutes. Three consecutive absences will lead to failure of the course.
2. Students wearing incomplete/improper uniform will not be admitted. Unnecessary jewelries must be removed.
3. Electronic devices must be turned off or muted during class discussion.
4. Requirements for the course must be submitted on time. Late projects will not be accepted.
5. Students who are cheating will not receive credit for quizzes or tests.

X. Prepared by: JOHN PEDRICK E. HILOT

Instructor

XI. Submitted to: RYAN G. FLORENCONDIA, LPT, D-Hum., Ph.D.

Director for Instruction
XII. Approved by: JUNREY P. PETERE, LPT, Ed.D., Ph.D-Hum, FRIEdr, Ph.D.
Dean of Academic Affairs