Language Technologies

back to overview

Please note that the project factsheets will no longer be updated.  All information relevant to the project can be found on the CORDIS factsheet.  This is updated on a regular basis with public deliverables, etc.

CASMACAT - Cognitive Analysis and Statistical Methods for Advanced Computer Aided Translation

287576 - STREP

At a glance

FP7-ICT-2011-7 - Language technologies Duration: 36 months Start date: 1 November 2011 End date: 31 October 2014 Project officer: Kimmo Rossi website

European integration and globalisation beyond it increases cross-border commercial, cultural, and political interaction. However, while the significance of political borders diminishes, the risk remains that the world will stays fractured by linguistic boundaries. The need to address each individual in a language that she speaks, and ideally in her native language, requires a huge amount of translation work.

Challenge

While there have been significant improvements to machine translation technology, the vast majority of this work is targeted towards bulk translation that is good enough or fit for use. A user on the Internet is satisfied with a rough translation, if it fills her information need. Opposed to that is the demand for high quality translations by the marketplace: the translation of reports and announcements of multi-national organizations, marketing material and product descriptions of commercial companies, and many other localization needs. Such high quality translations are still almost exclusively provided by human translators.

Goal

The project will build the next generation translator’s workbench to improve productivity, quality, and work practices in the translation industry. Based on insights gained in the cognitive studies, novel types of assistance will be developed

Innovation

The CASMACAT project will carry out cognitive studies of actual unaltered translator behaviour based on key logging and eye tracking. The acquired data will aid understanding how interfaces with enriched information are used, help to determine translator types and styles, and to build a cognitive model of the translation process.

• Interactive translation prediction, where the CASMACAT workbench makes suggestions to the human translator how to complete the translation. The project will adapt the existing interactive machine translation paradigm by adding input modalities, especially electronic pens and basing the suggestions on better exploitation of novel statistical machine translation models, such as ones based on syntactic structure.
• Interactive editing, where the CASMACAT workbench provides additional information about the confidence of its assistance, integrates translation memories, and assists authoring and reviewing.

Adaptive translation models, where the CASMACAT workbench learns from the interaction with the human translator by updating and adapting its models instantly based on the translation choices of the user.

The result

The CASMACAT project, in close collaboration with the MATECAT project, will develop a web-based workbench for translators targeted at the European localisation industry.

Impact

The proposed project will have impact on both academic research and on the translation industry. The academic impact will derive from the novel approach to building interactive MT systems: the CASMACAT methodology involves studying the behaviour of translators using MT systems, and using the resulting eye-tracking and user-activity data to inform system and user interface design.

back to overview