The University of Jordan
Natural Language Processing
Course ID: 1905380
14/07/2024 Dr. Loai Alnemer 1
The University of Jordan
Welcome to this course (by ChatGPT)
• In this course, you will learn the fundamental concepts and
techniques of Natural Language Processing (NLP), a field that
enables computers to understand, interpret, and generate
human language.
• Prepare to embark on an exciting journey as we explore the
cutting-edge applications of NLP in areas such as text analysis,
sentiment analysis, language generation, and more.
14/07/2024 Dr. Loai Alnemer 2
The University of Jordan
• "Natural language is the most important part of artificial
intelligence." John Searle
• "Natural language processing is a cornerstone of artificial
intelligence, allowing computers to read and understand
human language, as well as to produce and recognize
speech." Ginni Rometty
• "Natural language processing is one of the most
important fields in artificial intelligence and also one of
the most difficult." Dan Jurafsky
14/07/2024 Dr. Loai Alnemer 3
The University of Jordan
Lecture 1: Introduction and word vector
• The course (10 mins)
• Human language and word meaning (15 mins)
• Word2vec introduction (15 mins)
• Word2vec objective function gradients (25 mins)
• Optimization basics (5 mins)
• Looking at word vectors (10 mins or less)
14/07/2024 Dr. Loai Alnemer 4
The University of Jordan
Course Description
• This course provides an introduction to the field of natural language processing
(NLP) providing a theoretical foundation and hands-on (lab-style) practice in
computational approaches for processing natural language text. We will discuss
problems involving different language system components (such as meaning in
context and linguistic structures)
• Students will collaborate in teams on modeling and implementing natural
language processing and digital text solutions using Python and a variety of
relevant tools
• We will begin by discussing machine learning methods for NLP as well as core
NLP, such as language modeling, part of speech tagging, and parsing.
• We will also discuss applications such as information extraction, machine
translation, text generation, and automatic summarization
14/07/2024 Dr. Loai Alnemer 5
The University of Jordan
Course Objectives
By the end of this course, students will be able to:
• Understand the key concepts and principles of natural language processing.
• Implement common NLP techniques such as tokenization, stemming, lemmatization, and
part-of-speech tagging.
• Develop language models using n-grams and neural networks.
• Perform text classification, sentiment analysis, and named entity recognition.
• Build machine translation systems using sequence-to-sequence models.
• Explore advanced NLP topics such as dialogue systems, question answering, and text
generation.
• Apply NLP techniques to solve practical problems in various domains, such as customer
service, content analysis, and information retrieval.
14/07/2024 Dr. Loai Alnemer 6
The University of Jordan
Course work and grading policy
Collaboration policy:
• Project 15% - Don’t take code off the web
- Acknowledge working with other students
• Midterm 30% - Write your own assignment solutions
• Quizzes 5% - Students must independently submit their solutions
AI tools policy :Large language models are great (!), but
• Final Exam 50% • we don’t want ChatGPT’s solutions to our assignments
• Collaborative coding with AI tools is allowed; asking it to answer
questions is strictly prohibited
• Employing AI tools to substantially complete assignments will be
considered a violation of the Honor Code
14/07/2024 Dr. Loai Alnemer 7
The University of Jordan
What is NLP?
• NLP is a subfield of computer science and artificial intelligence (AI) that uses machine
learning to enable computers to understand and communicate with human language.
• NLP combines computational linguistics (rule-based modeling of human language) with
statistical modeling, machine learning, and deep learning to enable computers and
digital devices to recognize, understand, and generate text and speech.
• NLP research has enabled the era of generative AI, from large language models to image
generation models that can understand and respond to natural language requests.
• NLP is already widely applied in everyday technologies like search engines, chatbots,
voice assistants, and GPS systems.
• NLP also plays a growing role in enterprise solutions that help streamline and automate
business operations, increase employee productivity, and simplify mission-critical
business processes.
14/07/2024 Dr. Loai Alnemer 8
The University of Jordan
The term NLP
• Natural language: refers to the language that humans use to
communicate with each other, such as English, Spanish, or Arabic
• Processing: As distinguished from data processing Question: How is
data processing and natural language processing different?
14/07/2024 Dr. Loai Alnemer 9
The University of Jordan
Turing test
• NLP core technologies and methodologies arose from famous Turing
Test proposed by Sir Alan Turing (1912–1954) in 1950s, the father of
AI.
14/07/2024 Dr. Loai Alnemer 10
The University of Jordan
NLP Challenges
• Word sense ambiguity
14/07/2024 Dr. Loai Alnemer 11
The University of Jordan
NLP Challenges
• Word sense / meaning ambiguity Ambiguous headlines:
- Include your children when baking
cookies
- Safety Experts Say School Bus
Passengers Should Be Belted
Credit: http://stuffsirisaid.com
14/07/2024 Dr. Loai Alnemer 12
The University of Jordan
NLP Challenges
• Language is not static:
• Language grows
• Cyber language: BRB, G2G , ….
14/07/2024 Dr. Loai Alnemer 13
The University of Jordan
NLP Challenges
• Language is compositional
14/07/2024 Dr. Loai Alnemer 14
The University of Jordan
NLP Challenges
• Scale
• Huge amount of data
• Penn Tree bank ~1M from Wall street journal
• Newswire collection: 500M+
• Wikipedia: 2.9 billion word (English)
• Web: several billions of words
14/07/2024 Dr. Loai Alnemer 15
