REVEAL THIS: retrieval of multimedia multilingual content for the home user in an information society
Stelios Piperidis, Haris Papageorgiou · 2005
REVEAL THIS addresses a basic need underlying content organisation, filtering, consumption and enjoyment by developing content programming systems that will help European citizens keep up with the explosion of digital content scattered over different platforms (radio, TV, World Wide Web, etc), different media (speech, text, image, video) and different languages. REVEAL THIS aims at developing content programming technology able to capture, semantically index, categorize and cross-link multiplatform, multimedia and multilingual digital content, as well as provide the system user with semantic search, retrieval, summarization and translation functionalities. The innovative aspects of the project spring out of the main scientific and technological challenges: 1) semantic enrichment of multilingual multimedia content with topic, entity and fact information relevant to user profiles; 2) development of suitable cross-language, cross-media representations; and 3) deployment of the above in building search, retrieval, classification and summarization capabilities. We exploit explicit cross-media links and implicit links uncovered by methods such as latent semantic analysis and kernel canonical correlation analysis. Adequate cross-language capabilities (cross-language information retrieval, categorization and machine translation of indicative summaries) will be provided by the latest statistical machine translation technology.