Monnet (Multilingual ONtologies for NETworked knowledge), launched in March 2010, is a EU-funded project in the field of Language Technologies within the ICT programme of the 7th Framework.
Monnet is working on solutions that aim at facilitating access to on-line information across a range of languages. The initial step for Monnet is to set up infrastructures for extracting, representing and accessing knowledge across languages, using a novel combination of Semantic Web technology and automatic machine translation.
Current approaches to cross-lingual information access provide only partial solutions that address the problem in a restricted way, operating only at the document level without addressing either uniform extraction, representation, integration and querying of information across different languages and heterogeneous (textual, semi-structured, structured) data sources. Hence, the state of the art in machine translation is still far from providing multilingual services in specific domains.
A key aspect of the solution Monnet is working on is reflected by the fact that the technologies deployed in the project are dealing with information at the semantic level, i.e. by abstracting away over language(s) and form of the documents, allowing for a more advanced and uniform cycle of information processing (extraction and integration) and presentation of multilingual information. For this Monnet will work mainly on the development of three components, based on a new model for representing linguistic information in ontologies:
- Multilingual Ontology Localisation: Creates a lexicon in a target language from a lexicon in a source language, semi-automatically
- Cross-Lingual Ontology-based Information Extraction: Uses localized ontologies for the semantic-level extraction and integration of information from text and (semi-) structured data across languages
- Cross-Lingual Knowledge Access and Presentation Framework: Uses localized ontologies for the quick customization of knowledge access systems to other languages
The project is validating its approach to enabling the multilingual web in the context of two use cases, one in the field of e-Government and one in the field of financial and business information.
- National University of Ireland Galway , Irland
- DFKI , Deutschland
- Universität Bielefeld , Deutschland
- Universidad Politénica de Madrid , Spanien
- SAP , Deutschland
- XBRL Europe , Belgien
- Be Informed , Niederlanden