Message

F1523 Digital Tools for Humanities (Cultural Heritage Sp. Track)

Balletti Caterina, Boschetti Federico

First module – Prof. Balletti

The digital imaging in Humanities and Cultural Heritage has become commonplace generally to provide accurate and detailed records, and to facilitate detailed analysis of objects, documents, buildings, and artifacts, to increase public access.
Digital imaging technologies have developed rapidly in the last ten years, becoming more popular nowadays than their analogue counterparts, and increasing expectations from the general public about the range and quality of digital image material which should be made available by heritage institutions.
Today there are many tools, techniques, and methodologies in creating and disseminating digital image representations of cultural heritage, architecture and territory. Cultural Heritage Imaging (CHI) fosters the development and adoption of technologies for digital capture and documentation of the world's cultural, scientific, and artistic treasures.


Second module – Prof. Boschetti
In the last years, the amount of multilingual documents on the web has dramatically increased, but the web is still surfed in most cases by monolingual or bilingual users, not by polyglots. Consequently, a mine of relevant information is unreachable behind the linguistic barrier: good answers need good questions. This second module of the course aims at addressing the new challenges of the multilingual web by describing some solutions. In particular, cross-language information retrieval systems provide the user with methods and tools to translate both the query and the retrieved documents. In this way, it is possible to increase the accuracy of the search engines and maximize the exploitation of multilingual documents for domain-specific research purposes (e.g. in the architectural or archaeological domain). For instance, we can realize that a document about the Renaissance, available on the web, written in Italian and never translated before, is relevant to our reserach even if we do not master the language at the highest level. The terminology and named entity extraction will help us for a coarse translation in order to understand the general meaning and will help us to decide if further investigation (maybe by a mother-tongue translator) is necessary.


Teaching Method
Lectures are aimed at providing a theoretical explanation and a consistent knowledge on digital documentation; a pratical lab will be done to obtain an active participation by the students through class-exercise and case analysis. Slideshows, videos and software application are to be considered essential part of the programme.

Second Module: Lectures provide the theoretical background for the second module of the course. Students attend the hands-on lab, in order to master methods and tools for cross-language information retrieval applied to case studies discussed with the teacher and the classmates. The second module of the course requires slideshows, the development of simple scripts in Python and the use of web applications.


Learning objectives
The course covers the principles and techniques to create digital images by integrating the traditional of Computer Graphics with the most innovative one of Computational Photography.
At the end of the course, students will have the knowledge to:
1- develop an understanding of the digital processes of documentation;
2- choose the right digital tool respect their field of interest.
Moreover they will have a collection of software (freeware and shareware) and the knowledge to use them, considering their field of interest.

The second module of the course affords methods and techniques to retrieve relevant information from the multilingual web, by increasing precision and recall of the search.
At the end of the module, students will be able:
1. to understand the principles of the multilingual web;
2. to retrieve relevant documents for their domain-specific information needs expressed in languages that they only partially master or that they do not master at all;
3. to exploit multilingual documents retrieved from the web for their research purposes.