The CasMaCat project will build the next generation translator’s workbench to improve productivity, quality, and work practices in the translation industry.
Cognitive studies of actual unaltered translator behaviour based on key logging and eye tracking will be carried out. The acquired data will be examined for how interfaces with enriched information are used, to determine translator types and styles, and to build a cognitive model of the translation process.
Based on insights gained in the cognitive studies, novel types of assistance to human translators will be developed and integrated them into a new workbench, consisting of an editor, a server, and analysis and visualisation tools. The workbench will be designed in a modular fashion and can be combined with existing computer aided translation tools.
New types of assistance will be developed along the following lines: (1) Interactive translation prediction, where the workbench makes suggestions to the human translator how to complete the translation. We 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. (2) Interactive editing, where the workbench provides additional information about the confidence of its assistance, integrates translation memories, and assists authoring and reviewing. (3) Adaptive translation models, where the 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 workbench’s effectiveness will be demonstrated in extensive field tests at a translation agency. In addition, the language service industry and online volunteer translation platforms will also be considered. The outcome of the CasMaCat project will be made available as open source software to industry, academia, and to individual end users.