Eye-tracking and keyboard logging data have become established methods for the investigation of written text production, including authoring, translation, revision, post-editing of Machine Translation, etc. but can also be used for spoken translation or interpretation. Collecting and analyzing behavioral data (reading, writing, hearing, speaking) is a challenging task that requires advanced technologies for data acquisition and synchronization, but promises deeper insights into the human cognitive processes during text production. It allows for better grounded and more general theories of the human mind.
The course focuses on the analysis of human translation behavior; it addresses state-of-the-art topics in TPR, including data collection, storage, processing, and evaluation. It introduces the CRITT Translation Process Research Database (TPR-DB), a large repository of available legacy data, against which results of individual experiments can be matched and compared. The course is comprised of lectures, demos, and hands-on sessions in which key tools, methods and techniques for TPR are discussed. Basic knowledge of Python is desirable.
