WORKSHOP ON MULTIMODAL OUTPUT GENERATION (MOG 2010)

An important aspect of the new generation of intelligent systems is the possibility to employ more than one output modality when interacting with the user. A quick and successful interaction is expected when, for instance, the system’s output is presented to the user via multimedia/hypermedia in which text and graphics are merged, or by a conversational agent that combines the use of speech and gesture. In such multimodal systems sophisticated specifications are needed to combine the different output modalities in such a way that each bit of information is presented in the most appropriate manner (i.e., the system should select the most suitable modalities and modality combinations to convey information to the user).

The MOG 2010 workshop aims to bring work on multimodal output generation from different disciplines together to establish common ground and discuss possible future collaborations. Besides contributions from research fields such as multimodal language generation and embodied conversational agents, we would like to bring in an additional angle by investigating how research on multimodal output generation can benefit from a non-engineering perspective on multimodality. For example, how can research done in psychology and cognitive sciences, related to understanding how humans perceive and process multimodal information, be properly formalized for the purposes of intelligent multimodal output generation? And to what extent is it possible to formalize existing theories about how meaning is made in multimodal communication and use that for generating more meaningful multimodal output in the context of intelligent systems?

Thus, we invite technically oriented contributions as well as work in the area of human communication, such as cognitive models of multimodal communication and interaction. In this way we hope to combine an AI/engineering perspective with input from other disciplines such as linguistics and psychology, providing a forum where international researchers from different disciplinary backgrounds can exchange ideas on multimodal output generation and engage in scientific research collaboration.

MOG 2010 is a follow-up of MOG 2008, the workshop on Multimodal Output Generation organized on April 3-4, 2008, at the University of Aberdeen. and MOG 2007, the workshop on Multimodal Output Generation organized on January 25-26, 2007, at the University of Aberdeen.


Home Submission Program Committee Invited Speakers Registration Practical Information Proceedings Endorsement Contact	An important aspect of the new generation of intelligent systems is the possibility to employ more than one output modality when interacting with the user. A quick and successful interaction is expected when, for instance, the system’s output is presented to the user via multimedia/hypermedia in which text and graphics are merged, or by a conversational agent that combines the use of speech and gesture. In such multimodal systems sophisticated specifications are needed to combine the different output modalities in such a way that each bit of information is presented in the most appropriate manner (i.e., the system should select the most suitable modalities and modality combinations to convey information to the user). The MOG 2010 workshop aims to bring work on multimodal output generation from different disciplines together to establish common ground and discuss possible future collaborations. Besides contributions from research fields such as multimodal language generation and embodied conversational agents, we would like to bring in an additional angle by investigating how research on multimodal output generation can benefit from a non-engineering perspective on multimodality. For example, how can research done in psychology and cognitive sciences, related to understanding how humans perceive and process multimodal information, be properly formalized for the purposes of intelligent multimodal output generation? And to what extent is it possible to formalize existing theories about how meaning is made in multimodal communication and use that for generating more meaningful multimodal output in the context of intelligent systems? Thus, we invite technically oriented contributions as well as work in the area of human communication, such as cognitive models of multimodal communication and interaction. In this way we hope to combine an AI/engineering perspective with input from other disciplines such as linguistics and psychology, providing a forum where international researchers from different disciplinary backgrounds can exchange ideas on multimodal output generation and engage in scientific research collaboration. MOG 2010 is a follow-up of MOG 2008, the workshop on Multimodal Output Generation organized on April 3-4, 2008, at the University of Aberdeen. and MOG 2007, the workshop on Multimodal Output Generation organized on January 25-26, 2007, at the University of Aberdeen.
Endorsed by:
	L A T E S T N E W S Jan 21, 2010: A Best Student Paper Award will by sponsored by the Cognitive Science Society. Jan 18, 2010: Second call for papers.

Endorsed by: