2. Teaching
  3. International Teaching
  4. Single courses (exams) taught in english language

NATURAL LANGUAGE PROCESSING AND LARGE LANGUAGE MODELS

International Teaching NATURAL LANGUAGE PROCESSING AND LARGE LANGUAGE MODELS

Back

0622700126
DEPARTMENT OF INFORMATION AND ELECTRICAL ENGINEERING AND APPLIED MATHEMATICS
EQF7
COMPUTER ENGINEERING
2025/2026

YEAR OF COURSE 2
YEAR OF DIDACTIC SYSTEM 2022
SPRING SEMESTER
CFUHOURSACTIVITY
324LESSONS
324LAB
NICOLA CAPUANO T Curriculum
-
Objectives
THE COURSE PROVIDES THE THEORETICAL, METHODOLOGICAL, TECHNOLOGICAL, AND OPERATIONAL KNOWLEDGE RELATED TO THE AUTOMATIC UNDERSTANDING OF LANGUAGE AND TEXT, FRAMING THE INNOVATIVE PARADIGMS INTRODUCED BY LARGE LANGUAGE MODELS WITHIN THE GENERAL FRAMEWORK FOR THE IMPLEMENTATION OF NATURAL LANGUAGE PROCESSING SYSTEMS AND THE NUMEROUS MODERN APPLICATIONS OF THESE TECHNOLOGIES.

KNOWLEDGE AND UNDERSTANDING
BASIC CONCEPTS ON NATURAL LANGUAGE PROCESSING SYSTEMS. STANDARD LANGUAGE MODELS. LARGE LANGUAGE MODELS BASED ON TRANSFORMERS. NATURAL LANGUAGE PROCESSING APPLICATIONS WITH LARGE LANGUAGE MODELS. PROMPT ENGINEERING. FINE TUNING OF LARGE LANGUAGE MODELS.

ABILITY TO APPLY KNOWLEDGE AND UNDERSTANDING
DESIGN AND IMPLEMENTATION OF A NATURAL LANGUAGE PROCESSING SYSTEM BASED ON LARGE LANGUAGE MODELS, EFFECTIVELY INTEGRATING EXISTING TECHNOLOGIES AND TOOLS AND OPTIMALLY CONFIGURING THE OPERATING PARAMETERS
Prerequisites
PROPAEDEUTIC EXAM: MACHINE LEARNING
Contents
TEACHING UNIT 1: FUNDAMENTALS OF NATURAL LANGUAGE PROCESSING
(LESSON/PRACTICE/WORKSHOP HOURS 8/8/0)
- 1 (2 HOURS LESSON): BASIC CONCEPTS, TASKS, EVOLUTION AND APPLICATIONS OF NATURAL LANGUAGE PROCESSING
- 2 (2 HOURS LESSON): REPRESENTING A TEXT, TOKENIZATION, STEMMING, POS TAGGING, LEMMATIZATION
- 3 (2 HOURS PRACTICE): INTRODUCTION TO THE SPACY FRAMEWORK, NAMED ENTITY RECOGNITION, DEPENDENCY PARSING
- 4 (2 HOURS LESSON): BAG OF WORDS, TF-IDF VECTORS, VECTOR SPACE MODEL, DOCUMENT SIMILARITY
- 5 (2 HOURS PRACTICE): TEXT CLASSIFICATION, TOPIC LABELING EXAMPLE, HANDS-ON SENTIMENT ANALYSIS
- 6 (2 HOURS LESSON): WORD EMBEDDINGS, WORD2VEC, CBOW AND SKIP-GRAM ALGORITHMS, ALTERNATIVES (GLOVE, FASTTEXT)
- 7 (2 HOURS PRACTICE): USING PRE-TRAINED WES, TRAINING A WE MODEL, NEURAL NETWORKS AND TEXT ANALYSIS
- 8 (2 HOURS PRACTICE): APPLICATIONS OF RNNS, LSTMS, AND GRUS TO TEXT ANALYSIS, INTRODUCTION TO TEXT GENERATION
KNOWLEDGE AND UNDERSTANDING ABILITY: KNOWLEDGE OF THE BASIC CONCEPTS AND TECHNIQUES FOR THE PROCESSING OF NATURAL LANGUAGE.
APPLIED KNOWLEDGE AND UNDERSTANDING: APPLY BASIC CONCEPTS AND TECHNIQUES TO THE CREATION OF SIMPLE TEXT CLASSIFICATION AND ANALYSIS TOOLS.

TEACHING UNIT 2: FUNDAMENTALS OF LARGE LANGUAGE MODELS
(LESSON/PRACTICE/WORKSHOP HOURS 6/6/0)
- 1 (2 HOURS LESSON): INTRODUCTION TO LLMS
- 2 (2 HOURS LESSON): LLMS IN PRACTICE: TRAINING, FINE-TUNING, OUTPUT HANDLING
- 3 (2 HOURS PRACTICE): INTRODUCTION TO HUGGINGFACE
- 4 (2 HOURS LESSON): PROMPTING
- 5 (2 HOURS PRACTICE): INTRODUCTION TO LANGCHAIN AND LLAMAINDEX
- 6 (2 HOURS PRACTICE): PROMPTING WITH LANGCHAIN
KNOWLEDGE AND UNDERSTANDING: UNDERSTANDING OF BASIC CONCEPTS RELATED TO LARGE LANGUAGE MODELS.
APPLIED KNOWLEDGE AND UNDERSTANDING: DEVELOP SIMPLE LLM-BASED APPLICATIONS AND APPLY CORE PROMPT ENGINEERING TECHNIQUES.

TEACHING UNIT 3: RETRIEVAL-AUGMENTED GENERATION AND AGENTS
(LESSON/PRACTICE/WORKSHOP HOURS 6/6/0)
- 1 (2 HOURS LESSON): RETRIEVAL-AUGMENTED GENERATION (RAG)
- 2 (2 HOURS PRACTICE): HANDS-ON RAG AND LANGCHAIN (CHATBOT)
- 3 (2 HOURS LESSON): ADVANCED RAG
- 4 (2 HOURS PRACTICE): HANDS-ON ADVANCED RAG AND LLAMA
- 5 (2 HOURS LESSON): LLM-BASED AGENTS
- 6 (2 HOURS PRACTICE): HANDS-ON LLM AGENTS
KNOWLEDGE AND UNDERSTANDING: UNDERSTANDING OF BASIC CONCEPTS AND TECHNIQUES FOR RAG AND LLM-BASED AGENTS.
APPLIED KNOWLEDGE AND UNDERSTANDING: BUILD APPLICATIONS BASED ON RAG AND AGENTS TO SOLVE REAL-WORLD PROBLEMS OF VARYING COMPLEXITY.

TEACHING UNIT 4: LLM FINE TUNING
(LESSON/PRACTICE/WORKSHOP HOURS 4/4/0)
- 1 (2 HOURS LESSON): FINE-TUNING LLMS WITH PARAMETER-EFFICIENT TECHNIQUES
- 2 (2 HOURS PRACTICE): HANDS-ON FINE-TUNING
- 3 (2 HOURS LESSON): REINFORCEMENT LEARNING FROM HUMAN FEEDBACK (RLHF)
- 4 (2 HOURS PRACTICE): HANDS-ON RLHF
KNOWLEDGE AND UNDERSTANDING: KNOWLEDGE OF BASIC AND ADVANCED TECHNIQUES FOR FINE-TUNING LARGE LANGUAGE MODELS.
APPLIED KNOWLEDGE AND UNDERSTANDING: APPLY FINE-TUNING TECHNIQUES TO ADAPT LLMS TO SPECIFIC APPLICATION NEEDS.

TOTAL HOURS LECTURE/PRACTICE/LABORATORY 24/24/0
Teaching Methods
THE COURSE INCLUDES LECTURES AND CLASSROOM EXERCISES. THE LECTURES WILL PROVIDE STUDENTS WITH FUNDAMENTAL KNOWLEDGE ON THE MAIN BASIC AND ADVANCED TECHNIQUES FOR THE REPRESENTATION, ANALYSIS AND CLASSIFICATION OF TEXT IN NATURAL LANGUAGE WITH LARGE LANGUAGE MODELS. THE EXERCISES WILL DEVELOP THE ABILITY TO APPLY THESE TECHNIQUES TO THE CREATION OF TEXT CLASSIFICATION AND ANALYSIS AND QUESTION ANSWERING TOOLS. PARTICIPATION IN LECTURES IS MANDATORY AND A MINIMUM ATTENDANCE OF 70% IS REQUIRED TO TAKE THE EXAM. ATTENDANCE WILL BE MONITORED VIA THE AUTOMATIC EASYBADGE SYSTEM PROVIDED BY THE UNIVERSITY.
Verification of learning
THE EXAM CONSISTS OF A PROJECT WORK AND AN ORAL TEST. THE PROJECT WORK REQUIRES STUDENTS TO CRITICALLY APPLY THE METHODOLOGIES LEARNED DURING THE COURSE TO A PRACTICAL CASE. THE ORAL TEST WILL EVALUATE THE THEORETICAL SKILLS ACQUIRED DURING THE COURSE, THE ABILITY TO ARGUE THE DESIGN CHOICES MADE IN THE PROJECT WORK AND TO ANSWER QUESTIONS ON SPECIFIC TOPICS COVERED IN THE LECTURES. THE FINAL MARK WILL BE DETERMINED BY THE AVERAGE OF THE MARKS OBTAINED IN THE TWO TESTS.
Texts
REFERENCE TEXTS:

H. LANE, C. HOWARD, H. M. HAPKE: NATURAL LANGUAGE PROCESSING IN ACTION, 2ND EDITION, MANNING, 2025.

L.F. BOUCHARD, L. PETERS: BUILDING LLMS FOR PRODUCTION, TOWARDS AI, 2024.

SUPPLEMENTARY TEACHING MATERIALS WILL BE AVAILABLE IN THE DEDICATED SECTION OF THE COURSE ON THE UNIVERSITY’S E-LEARNING PLATFORM (HTTPS://ELEARNING.UNISA.IT), ACCESSIBLE TO ENROLLED STUDENTS USING THEIR UNIVERSITY CREDENTIALS.
  BETA VERSION Data source ESSE3