< Back to list

From Linguistic Linked Open Data to Multimodal Natural Interaction: A Case Study

conferencePaper

DOI:10.1109/iV.2018.00060
Authors: Grazioso Marco / Cera Valeria / Di Maro Maria / Origlia Antonio / Cutugno Francesco

Extracted Abstract:

β€”We present here the conversion of Linguistic Linked Open Data into Semantic Maps to be used to produce contents in a set of technological applications for Cultural Heritage. The paper describes the architec- tural data collection and annotation procedure adopted in the Cultural Heritage Orienting Multimodal Experi- ences (CHROME) project (PRIN 2015 funded by Italian University and Research Ministry). Such data will be used in Multimodal Dialogue Systems to obtain precise information about Architectural Heritage, by means of pointing gestures or verbal requests. In particular, we de- sign conversational agents accessing fine-detailed semantic data linked to available 3D models of historical buildings. The starting point of our scientific approach is the Getty Vocabulary on Art & Architecture Thesaurus, integrated with the Getty Thesaurus of Geographic Names (TGN) and the Union List of Artist Names (ULAN). These data are related to 3D mesh of the considered buildings in order to associate abstract concepts to architectural elements. In the field of 3D architectural investigation, a significant amount of research has been conducted to allow domain experts to represent semantic data while keeping spatial references. We will discuss how this will make it possible to support multimodal user interaction and generate Cultural Heritage presentations. I.

Level 1: Include/Exclude

  • Papers must discuss situated information visualization* (by Willet et al.) in the application domain of CH.
    *A situated data representation is a data representation whose physical presentation is located close to the data’s physical referent(s).
    *A situated visualization is a situated data representation for which the presentation is purely visual – and is typically displayed on a screen.
  • Representation must include abstract data (e.g., metadata).
  • Papers focused solely on digital reconstruction without information visualization aspects are excluded.
  • Posters and workshop papers are excluded to focus on mature research contributions.
Show all meta-data