| Skip to main content | Skip to sub navigation |

This is now an inactive research group it's members have moved on. You can find them at their new research groups:

ECS Intranet:
Statistical Multi-Lingual Analysis for Retrieval and Translation (SMART)

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 promising, 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. As an example, even though lexical choice is usually more accurate with Statistical Machine Translation (SMT) systems than with their rule-based counterparts, the text they produce tends to be less fluent. As a second example, SMT systems are trained in batch mode and do not adapt by taking user feedback into account. Finally, in Cross-Language Information Retrieval tasks, query words are most often translated independent of one another, thus giving up possibly relevant contextual clues.

SMART is an attempt to address these and other shortcomings by the methods of modern Statistical Learning. The 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 three 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.

SMART is a 3-year "Specific Target Research Project" (STReP) funded by the European Commission through its "Information Society Technologies" (IST) priority, as part of the sixth Framework Programme. It started on October 1, 2006 and is coordinated by Nicola Cancedda at Xerox Research Centre Europe.

Homepage: http://www.smart-project.eu/
Type: Normal Research Project
Research Group: Information: Signals, Images, Systems Research Group
Themes: Machine Translation, Machine Learning
Dates: 1st October 2006 to 30th September 2009



Principal Investigators

Other Investigators

URI: http://id.ecs.soton.ac.uk/project/441
RDF: http://rdf.ecs.soton.ac.uk/project/441

More information

You can edit the record for this project by visiting http://secure.ecs.soton.ac.uk/db/projects/editproj.php?project=441