Multilingual content aggregation system based on trust search engine

Project Information

M-CAST

Grant agreement ID: 22249

Project closed

Start date 1 January 2005

End date 31 December 2006

Funded under

• Multiannual Community programme to stimulate the development and use of European digital content on the global networks and to promote linguistic diversity in the Information Society 2001-2005

Total cost No data

EU contribution € 1 680 000,00

Coordinated by

Synapse Développement (SYN)
France

Objective

The aim of the project is to develop a multilingual infrastructure enabling content producers to access, search, and integrate the assets of large multilingual text (and multimedia) collections, such as Internet libraries, resources of publishing houses, press agencies and scientific databases.

M-CAST will allow for the establishment of Digital Libraries by aggregating digital data available in different formats and locations. The system will be tested by two libraries, for which Multimedia Content Aggregation Portals (M-CAPs) will be established, using their existing portals and infrastructures. These portals will allow finding answers to natural language queries in large digital collections of multilingual data. The presentation layer of the portals will be multimedia capable, allowing for presentation of digitalized copies of old printings, legal documents, music scores, pictures, video etc., while only their textual descriptions can be indexed.

M-CAST will be based on the outcome of the TRUST - Multilingual Semantic and Cognitive Search Engine for Text Retrieval Using Semantic Technologies (IST-1999-56416) project financed under the 5th EU Framework Programme for RTD (). The portals will be deployed and tested in two public libraries: the Polish Internet Library and the National Library of the Czech Republic to make their digital resources available online for finding answers to natural language queries in multilingual digital collections.

At the end of the project a marketable product for multilingual knowledge management purposes will be available. Commercial exploitation of the results in libraries (information retrieval, classified catalogues), collection management (data acquisition and aggregation, circulation statistics, weeding), bibliographic databases, information services (selective dissemination of information, personalisation, knowledge discovery) and in semantic data networks is foreseen.

Programme(s)

• IS-ECONTENT - Multiannual Community programme to stimulate the development and use of European digital content on the global networks and to promote linguistic diversity in the Information Society 2001-2005

Topic(s)

• AL1 - Action Line 1: Improving access to and expanding the use of public sector information

Call for proposal

Data not available

Funding Scheme

DEM - Demonstration contracts

Coordinator

Synapse Développement (SYN)

• EU contribution: No data
• Address: Rue Maynard, 33 ; 31000 Toulouse ; France
• Total cost: No data

Participants (3)

National Library of the Czech Republic (NLP) Národní knihovna Ceské republiky (NKP)

Czechia

• EU contribution: No data
• Address: Klementinum, 190 ; 110 00 Prague 1
• Total cost: No data

Priberam Informática (PRI)

Portugal

• EU contribution: No data
• Address: Avda Defensores de Chaves, 32 - 3º Esq. ; 1000-119 Lisboa
• Total cost: No data

ToExpert System S.p.A. (ExpSys)

Italy

• EU contribution: No data
• Address: Via Virgilio, 56/Q - Scala 5 ; 41100 Modena
• Total cost: No data