Studying at the University of Verona
Here you can find information on the organisational aspects of the Programme, lecture timetables, learning activities and useful contact details for your time at the University, from enrolment to graduation.
Study Plan
This information is intended exclusively for students already enrolled in this course.If you are a new student interested in enrolling, you can find information about the course of study on the course page:
Laurea magistrale in Artificial Intelligence - Enrollment from 2025/2026The Study Plan includes all modules, teaching and learning activities that each student will need to undertake during their time at the University.
Please select your Study Plan based on your enrollment year.
1° Year
| Modules | Credits | TAF | SSD |
|---|
2 modules among the following (A.A. 2024/2025 Network Science not activated)1 module among the following2° Year It will be activated in the A.Y. 2025/2026
| Modules | Credits | TAF | SSD |
|---|
| Modules | Credits | TAF | SSD |
|---|
2 modules among the following (A.A. 2024/2025 Network Science not activated)1 module among the following| Modules | Credits | TAF | SSD |
|---|
2 modules among the following (1st year: Knowledge representation, Natural language processing, HCI Intelligent interfaces - 2nd year: AI & Cloud - 1st and 2nd year: Computer Vision & Deep learning)2 modules among the following (1st year: Knowledge representation, Natural language processing, HCI Intelligent interfaces - 2nd year: AI & Cloud, Visual intelligence, Statistical learning - 1st and 2nd year: Computer Vision & Deep Learning)Legend | Type of training activity (TTA)
TAF (Type of Educational Activity) All courses and activities are classified into different types of educational activities, indicated by a letter.
Natural Language Processing (2024/2025)
Teaching code
4S010677
Teacher
Coordinator
Credits
6
Language
English
Scientific Disciplinary Sector (SSD)
ING-INF/05 - INFORMATION PROCESSING SYSTEMS
Period
Semester 1 dal Oct 1, 2024 al Jan 31, 2025.
Courses Single
Authorized
Learning objectives
The course covers the five basic areas of development of technique for the analysis of natural language: text analytics, statistical natural language processing, morpho-syntatic analysis, semantic analysis, natural logic. Specifically, the student will know segmentation techniques, stemming and lemmatization methods, POS tagging, Sentence split, logical representation of language and language-specific method for “common” morphosyntax, and more generally for those languages that have been represented with generative and categorical grammar methods. Methods based on neural networks, such as Transformers, will also be addressed in the course. Above mentioned techniques will be applied to in corpora text analysis, open and closed QA systems, machine translation and to technologies for natural language generation.
Prerequisites and basic notions
Basic notions of Logic and Machine Learning
Program
1. Basics of text processing
1.1 Regular Expressions, Text Normalization, Edit Distance
1.2 N-gram Language Models
1.3 Naive Bayes and Sentiment Classification
2. Statistical natural language processing
2.1 Logistic Regression
2.2 Vector Semantics and Embeddings
2.3 Neural Networks and Neural Language Models
2.4 Sequence Labeling for Parts of Speech and Named Entities
2.5 Machine Translation
3. Symbolic methods for NLP
3.1 Constituency Grammars
3.2 Constituency Parsing
3.3 Dependency Parsing
4. Semantic technologies for NLP
4.1 Logical Representations of Sentence Meaning
4.2 Semantic technologies
4.3 Computational Semantics and Semantic Parsing
4.4 Information Extraction
4.4 Word Senses and WordNet
4.5 Semantic Role Labeling and Argument Structure
4.6 Lexicons for Sentiment, Affect, and Connotation
5. Advanced issues for text processing
5.1 Coreference Resolution
5.2 Discourse Coherence
6. Applications of NLP
6.1 Question Answering
6.2 Chatbots and Dialogue Systems
Bibliography
Didactic methods
Introductory lesson to individual topics, exercises for individual topics and review of a group of topics as scheduled in preparation for the exam.
Learning assessment procedures
To pass the exam, students must show:
- to have understood the principles underlying the functioning of automatic natural language processing
- to be able to present their arguments in a precise and organic way without digressions,
- to know how to apply the acquired knowledge to solve application problems.
Exam consists of three homework pieces and an oral optional examination.
Evaluation criteria
Correctness and completeness of the assigned works, correctness and completeness of the oral presentation.
Criteria for the composition of the final grade
The final grade is formed through the sum of the three tests, each evaluated in tenths, to which is added a score from 0 to 5 which evaluates the oral test, up to saturation. The score of 30 with honors can only be obtained if the three tests assigned at home are rated 10 each and the oral test is worth at least 3.
Exam language
English
