@phdthesis{Garoufi2013,
  author    = {Garoufi, Konstantina},
  title     = {Interactive generation of effective discourse in situated context : a planning-based approach},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-69108},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {As our modern-built structures are becoming increasingly complex, carrying out basic tasks such as identifying points or objects of interest in our surroundings can consume considerable time and cognitive resources. In this thesis, we present a computational approach to converting contextual information about a person's physical environment into natural language, with the aim of helping this person identify given task-related entities in their environment. Using efficient methods from automated planning - the field of artificial intelligence concerned with finding courses of action that can achieve a goal -, we generate discourse that interactively guides a hearer through completing their task. Our approach addresses the challenges of controlling, adapting to, and monitoring the situated context. To this end, we develop a natural language generation system that plans how to manipulate the non-linguistic context of a scene in order to make it more favorable for references to task-related objects. This strategy distributes a hearer's cognitive load of interpreting a reference over multiple utterances rather than one long referring expression. Further, to optimize the system's linguistic choices in a given context, we learn how to distinguish speaker behavior according to its helpfulness to hearers in a certain situation, and we model the behavior of human speakers that has been proven helpful. The resulting system combines symbolic with statistical reasoning, and tackles the problem of making non-trivial referential choices in rich context. Finally, we complement our approach with a mechanism for preventing potential misunderstandings after a reference has been generated. Employing remote eye-tracking technology, we monitor the hearer's gaze and find that it provides a reliable index of online referential understanding, even in dynamically changing scenes. We thus present a system that exploits hearer gaze to generate rapid feedback on a per-utterance basis, further enhancing its effectiveness. Though we evaluate our approach in virtual environments, the efficiency of our planning-based model suggests that this work could be a step towards effective conversational human-computer interaction situated in the real world.},
  language  = {en}
}