Educational Goals
The course objective is to provide a basic understanding of the concepts, methods and techniques for extracting relevant information from texts through the use of language technologies (Information Extraction). Particular attention will be devoted to the relationship between the nature and complexity of information to be acquired and the level of linguistic information needed, with the aim to provide students with basic skills on the main application area of Information Extraction.
Description
The course aims to illustrate the use of language technologies for research and intelligent management of the information contained in document collections of vast dimensions. In particular, we will describe different approaches to extract structured knowledge from texts, with particular attention to: i) the acquisition of terminological-conceptual knowledge on specialized domains, ii) recognition and semantic categorization of proper names and other entities relevant to the selected domain as well as relations and events involving them. The course includes the development of a project on topics and with software tools to be decided each year.