Teacher
Bernardo Magnini
Fondazione Bruno Kessler (FBK)
magnini[at]fbk.eu
INF01

Aim
The information society needs both rapid and sophisticated technologies able to extract knowledge from huge repositories of unstructured data. In this context, there is a growing demand for applications that perform strong text mining processing, including improving web search engines, providing services for human-machine interaction systems, e-learning, information extraction and opinion mining, and much more. The course will give an overview of methodologies and tools in the field of Computational Linguistics, useful for operating actively in this sector starting from a background both in computer science and in human sciences. We will provide an introduction to recent approaches and technologies in text mining, with particular attention to vector-based representations of word meanings and machine-learning algorithms.
Syllabus
·      Text mining: research field and applications
·      Machine learning approach: methodology, task definition, training and test data, evaluation metrics
·      Distributional semantics and embeddings
·      Deep learning for text mining: neural networks and transformers
·      A case study: sentiment analysis
Introductory readings
Pilehvar M.T. and Camacho-Collados J.: Embeddings in Natural language Processing, Synthesis Lectures on Human Language Technologies, Morgan&Claypool, 2021.

Course requirements 
None

Exam modality
Multiple-choice test

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

Schedule
27 February 2024, 10:00-13:00 (Room 2BC30)
5 March 2024, 10:00-13:00 (Room 2AB40)

Location
Rooms described in the schedule above and located at the Dept. of Mathematics

<< Courses in 2023-2024