Teacher
Giovanni Da San Martino
Dipartimento di Matematica, Università degli Studi di Padova,
giovanni.dasanmartino[at]unipd.it
INFO-01/A

Aim
The course reviews how words, sentences and entire documents are represented and some natural language processing tasks requiring ad hoc modeling strategies, such as information extraction and text span identification.

Syllabus
• Natural Language Processing pipelines versus end-to-end models
• How to represent words and sentences in a (machine-learning) algorithm
• Natural Language Processing tasks requiring ad hoc modeling: an overview

Introductory reading
None

Course requirements
Although the course will try not to assume any previous knowledge, having attended any basic machine learning course would help.

Examination
Modality - The PhD students will select a problem which is at the intersection of NLP and Neuroscience. They would critically analyse the state of the art and make a project proposal. It is also possible to provide experimental results. The students will be divided into cross-curricular groups (approximately four people per group). In the last lecture of the course the students would give a presentation about the work they have done. The work will be evaluated according to the scientific rigor demonstrated.
Goal - conducting rigorous interdisciplinary research.
Skills acquired with the exam - understanding of NLP tasks and applications; ability to work in an interdisciplinary group.
Feedback - Each group will receive feedback right after the presentation both by the teacher and the other students.

Course material, enrollment and last-minute notifications
Made available by the teacher at this Moodle address

Schedule
09 January 2025, 14:30-16:30 (Room 2AB40)
23 January 2025, 14:30-16:30 (Room 2AB40)
30 January 2025, 14:30-16:30 (Room 2AB40)
04 February 2025, 14:30-17:30 (Room 2AB40)
20 February 2025, 14:30-17:30 (Room 2AB40)

Location
Rooms written in the schedule above and located at the Dept. of Mathematics, via Trieste 63 Padova

<< Courses in 2024-2025