The following research projects have received external funding of more than DKK 500,000.
2011- 2014: Cognitive Analysis and Statistical Methods for Advanced Computer Aided Translation (CASMACAT)
This project seeks to advance computer-aided translation, and integrate novel models into a new open source workbench, in order to improve productivity of human translators by addressing their needs for the right type of assistance at the right time. An important objective of the CASMACAT project is to gain insight into the cognitive processes involved in human translation. Relying on key logging and eye-tracking, we study translator behaviour in computer-aided translation, and investigate the usefulness of visualisation options in post-editing and interactive translation, for different types of text, for different language pairs, and for translators with different degrees of expertise. The findings of this first stage provide the theoretical background for the CASMACAT work on interactive translation prediction and interactive editing, and are crucial for the development of the adaptable CASMACAT workbench. Based on the cognitive user model, it will anticipate user behaviour and tailor visualisation to the users’ immediate needs. Partners: University of Edinburgh, Universitat Politècnica de València, Celer Soluciones, and Copenhagen Business School. Members from CBS: Arnt Lykke Jakobsen, Michael Carl, Christopher Teplovs, and Jakob Elming.
Between 2011 and 2013, the Danish Agency for Sciences, Technology and Innovation supported the CRITT with international networking grants, under the following subtitles:
The network organized a large number of meetings, workshops and conferences in Denmark, India, Japan and the USA (see here). International partners of the network were:
2009-2011: Reconstruction of Speech Events in Real Time (DKK 4.7 million)
The project aims to rethink the way information is encoded in speech and decoded in hearing. Our formal models are optimized for compatibility with hearing aids, speech technology, and mobile telephony. We use methods from machine learning, numerical analysis, deductive systems, acoustic analysis, and natural language parsing, based on data from real-world and laboratory tasks. The project is funded by the Danish Research Council for the Humanities. Members: Peter Juel Henrichsen (principal investigator), Maya Borges, Ruben Schactenhaufen, Thomas Ulrich Christiansen (Technical University of Denmark), Andrea Corradini (University of Southern Denmark).
2008-2011: The Copenhagen Dependency Treebank (DKK 3.0 million)
This project seeks to build a set of parallel treebanks for Danish, English, German, Italian, and Spanish with 40,000 words in each language, based on a unified annotation scheme for syntax, morphology and discourse. The treebanks will then be used to explore a wide range of research problems in theoretical and computational linguistics. The project is funded by the Danish Research Council for the Humanities. Members: Matthias Buch-Kromann (principal investigator), Iørn Korzen, Henrik Høeg Müller, Martin Haulrich.
This project seeks to develop dependency-based models of human parsing and translation, exploring a new serial repair-based processing architecture based on local search. The project is funded by the Danish Research Council for the Humanities. Members: Matthias Buch-Kromann.
Using eyetracking, keylogging, voice recognition, and audio recording, this project explored the interaction of comprehension and production processes in hybrid forms such as sight translation, which is hybrid in the sense that it involves production of oral target text from a written source and therefore demonstrates a cross of features from traditional (written) translation and (oral) interpreting. The theoretical aim was to explore the different forms of interaction in closely related translation genres, and the practical aim was to demonstrate the positive and/or negative effects of convergence of the written and spoken modes. Members: Arnt Lykke Jakobsen (principal investigator), Barbara Dragsted, Inge Gorm Hansen. For results, see under Publications by the members of the research team.
Tools and Technologies for the Purposes of Studying Cognition and Translation (EU-FP6 project) This project sought to build an application that can be used at once for studying human translational behaviour and to support practical translation. The application interprets information about a translator's eye and finger movements, provides insight into comprehension processes and text production processes, and also finds out when a translator needs help and provides that help instantly. Partners: University of Tampere, New Bulgarian University, Tobii Technology AB, Technical University Graz, University of Oslo, Copenhagen Business School. Members from CBS: Arnt Lykke Jakobsen (principal investigator), Barbara Dragsted, Michael Carl, Christian Jensen, Kristian Tangsgaard Hvelplund Jensen, Annette Camilla Sjørup. For results, see under Publications. For detailed info on the entire project, see http://cogs.nbu.bg/eye-to-it/