Course

Course Summary
Credit Type:
Course
ACE ID:
SKIL-0281
Organization:
Location:
Online
Length:
22.5 hours (52 weeks)
Dates Offered:
Credit Recommendation & Competencies
Level Credits (SH) Subject
Lower-Division Baccalaureate 1 Natural Language Processing
Description

Objective:

The course objective is to embark on an enriching journey into the world of Natural Language Processing (NLP) and Large Language Models (LLMs). Beginning with the "Fundamentals of Natural Language Processing," participants will build a solid foundation in NLP techniques, mastering text preprocessing, representation, and classification. Moving forward, the "Natural Language Processing with Deep Learning" track delves into advanced deep learning methodologies for NLP tasks. In contrast, the "Natural Language Processing with LLMs" track pushes the boundaries with cutting-edge LLMs, attention mechanisms, and transformer architectures. From understanding attention mechanisms to implementing state-of-the-art LLMs for tasks like language translation and text summarization, this journey equips participants with the knowledge and skills to navigate the forefront of NLP innovation.

Learning Outcomes:

  • Apply deep learning techniques for NLP tasks, including recurrent networks and attention-based models like transformers.
  • Implement rule-based models, represent text as numeric features, and utilize word embeddings for sentiment analysis and relationship capture.
  • Understand the fundamentals of natural language processing (NLP) and text preprocessing using NLTK and SpaCy.
  • Work with tokenizers and fine-tune models in Hugging Face for tasks such as classification, question answering, language translation, and summarization.

General Topics:

  • Introducing Natural Language Processing
  • Preprocessing Text Using NLTK & SpaCy
  • Rule-based Models for Sentiment Analysis
  • Representing Text as Numeric Features
  • Word Embeddings to Capture Relationships in Text Natural Language Processing Using Deep Learning
  • Using Recurrent Networks for Natural Language Processing
  • Attention-based Models and Transformers for Natural Language Processing
  • Working with Tokenizers in Hugging Face Fine-tuning Models for NLP Tasks
Instruction & Assessment

Instructional Strategies:

  • Computer Based Training
  • Practical Exercises

Methods of Assessment:

  • Examinations
  • Quizzes

Minimum Passing Score:

70%
Supplemental Materials