Mednarodni projekti
Statistical Multilingual Analysis for Retrieval and Translation
Organizacije (2)
Povzetek
More than half of the EU citizens are not able to hold a conversation in a language other than their mother tongue, let alone to conduct a negotiation, or interpret a law. In a time of wide availability of communication technologies, language barriers are a serious bottleneck to European integration and to economic and cultural exchanges in general. More effective tools to overcome such barriers, in the form of software for machine translation and other cross-lingual textual information access tasks, are in strong demand. Statistical methods are a promising approach, in that they achieve performances equivalent or superior to those of rule-based systems, at a fraction of the development effort. There are, however, some identified shortcomings in these methods, preventing their broad diffusion. SMART is an attempt to address these shortcomings by deploying the methods of modern Statistical Learning. With this goal, SMART exactly targets strategic objective 2.5.7, which 'aims at developing natural and easy to use interfaces that communicate intelligently via several modalities or with multilingual capabilities'.\nThe scientific focus is on developing new and more effective statistical approaches while ensuring that existing know-how is duly taken into account. By bringing together leading research institutions in Statistical Learning, Machine Translation and Textual Information Access, the SMART consortium is well positioned to achieve this goal. Thorough field evaluation on two user scenarios, involving user groups from innovation-oriented SMEs, and extensive exploitation and dissemination activities will ensure that advances make their way out of the laboratories, in the form of both significant and measurable improvements over existing technologies and of new applications currently beyond the state of the art.
