Natural interaction & Embodied Communication


The text below refers to both embodied language processing and communication based on the oral language and its communicational, nonverbal-modality constituents (gestures, facial expressions, paralanguage, etc.) as well as on the visual language (Sign Language) that by definition serves as embodied language that merits linguistic analysis, resources creation, annotation & maintenance, specific HCI applications in the framework of “Design for All” principles and assistive technologies as well as technological tools implementation to serve the areas of SL synthesis, SL recognition and SL translation.

In the last decade, new findings and accounts of cognitive models had a major impact and influenced the way we view language technology in human communication. Among the most promising trends, Embodied Language Processing (ELP) embraces a multimodal approach including non-verbal behavioural cues and psychological variables such as attitude and affect. Embodied Language research & technology is a multidisciplinary field blending and fertilizing innovations and findings from social & cognitive psychology, speech and signal processing, neuroscience, computer vision and computational linguistics. Pioneering contributions are expected in the coming years, extending the focus on traditional linguistics. It is thus clear that new algorithms and technologies are required and computational frameworks need to accommodate the above into more sophisticated models. The ELP group focuses on (a) the integration of cognitive theories, knowledge representation models and algorithms in a computational framework enabling rich models of human-machine interaction, and (b) the development of novel machine learning techniques in the analysis of non-linear and socially situated multimodal streams in human communication. Successful analysis and understanding of social interactions would be the key in a number of rich applications, including:

  • Companions, personal assistants and social robots
  • Embodied conversational agents (ECAs), avatars
  • Applications in Health and Education, Ambient Intelligent applications
  • Multimodal & multiparty dialogue systems
  • Emotion recognition & Behavioural Analytics
  • Future smart environments, Ambient Assistive Living
  • Computational intelligence in games - storytelling 
Ινστιτούτο Επεξεργασίας του Λόγου