麻豆社

Argomenc dl curs
The course will provide an overview of Natural Language Processing (NLP) and give some insights on its application to Recommender Systems (RS). It will start by introducing the NLP field, its long-standing goals and motivations. Then it will consists of three main parts: I) it introduces: Language Models (n-grams); the move from LM to Neural LM by first diving into Distributional Semantics. the raise of Large Language Models. II) it discusses weakness and strengths of LLM with respect to the NLP long-standing challenges. In particular: Syntax, Semantics and Reasoning, Pragmatics and Dialogues, Visually Grounded Conversational systems III) it gives an overview of Recommender Systems (RS) and some insights on the application of NLP to RS. Parts I and II will complement the frontal classes with labs in which students will have hands-on experience on the topics introduced through the frontal classes.

Modalit茅 de ensegnament
Frontal lectures, exercises, labs, projects, seminars.

Obietifs formatifs
The course belongs to the type "caratterizzanti 鈥� discipline informatiche" in the curricula 鈥淒ata Analytics鈥�. The main objective of the course is to a) reach an overview of Natural Language Processing (NLP) and its application to Recommender Systems (RS); and to familiarize with b) a variety of approaches and c) evaluation methods. Hence, the student will familiarize with today's NLP models and their application to RS situating them in the broader and long-standing context of the field. Applying knowledge and understanding: - D1.2 - Understanding of the skills, tools and techniques required for an effective use of data science - D1.7 - Knowledge of artificial intelligence techniques and methods for the implementation of intelligent systems Applying knowledge and understanding: - D2.1 - Practical application and evaluation of tools and techniques in the field of data science - D2.2 - Ability to address and solve a problem using scientific methods - D2.6 - Ability to apply innovative techniques of data mining and machine learning to extract knowledge from complex and heterogeneous data Making judgments - D3.2 - Ability to autonomously select the documentation (in the form of books, web, magazines, etc.) needed to keep up to date in a given sector Communication skills - D4.1 - Ability to use English at an advanced level with particular reference to disciplinary terminology - D4.3 - Ability to structure and draft scientific and technical documentation Learning skills - D5.2 - Ability to autonomously keep oneself up to date with the developments of the most important areas of data science - D5.3 - Ability to deal with problems in a systematic and creative way and to appropriate problem solving techniques

Sort de ejam
- Mid-term assignments (e.g. Quiz, code assignment, Seminars), 20% - Project in a small team (2 students), 40% - Final exam, written, 40 % of mark The mid-term assignments will help students monitor their understanding of the topics introduced during the course. To this end, we will use quiz, and presentations of assignments such as coding and/or understanding scientific paper, chosen from the list of papers given by the lecturer. The presentation is aimed at assessing to what extent the student has achieved the above-mentioned learning outcomes related to: applying knowledge and understanding, making judgments, communication and learning skills. The project will consist on the proposal for the evaluation of an NLP model against a specific task. The project domain, the attacked problem, the techniques and the obtained results, if any, must be described in a report (~4 pages of ACL latex style). The project is aimed at assessing to what extent the student has achieved the above-mentioned learning outcomes related to: applying knowledge and understanding, making judgments, and communication skills. The written exam is based on verification questions and exercises, and it will assess to what extent the student has achieved the above-mentioned learning outcomes related to: knowledge and understanding, applying knowledge and understanding, and learning skills.

Criters de valutazion
The mid-term assignment will be evaluated at the end of the semester and it is a prerequisite for attending the written exam. The project report must be submitted one week before the written exam. The student must pass each single component of the exam (mid-term assignment, project and written exam), by obtaining at least 50% of the mark. Presentation evaluation: clarity of the presentation and capability to reply to clarification questions of the teacher. Project evaluation criteria: clarity of the presentation, novelty of the problem and the solution, appropriateness of the methods, significance of the solution and capability to refer to the methods and techniques discussed in the course. Written exam: correctness and clarity of the replies to the posed questions. Students who do not attend classes have to contact the lecturer at least one month before the written exam.

Bibliografia obligatora

(3rd ed. 2025), Dan Jurafsky and James H. Martin

All the required reading material will be provided during the course and will be available in electronic format. Copy of the slides will be available as well.

Subject Librarian: David Gebhardi, David.Gebhardi@unibz.it

Bibliografia aconsieda

Scientific papers and additional books will be specified on each course topic during lectures.

Depl霉 informazions
Software used: Python