Domain Directed Dialogs for Decision Processes

Computer Science – Other Computer Science

Scientific paper

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

Scientific paper

The search for a standardized optimum way to communicate using natural language dialog has involved a lot of research. However, due to the diversity of communication domains, we think that this is extremely difficult to achieve and different dialogue management techniques should be applied for different situations. Our work presents the basis of a communication mechanism that supports decision processes, is based on decision trees, and minimizes the number of steps (turn-takes) in the dialogue. The initial dialog workflow is automatically generated and the user's interaction with the system can also change the decision tree and create new dialog paths with optimized cost. The decision tree represents the chronological ordering of the actions (via the parent-child relationship) and uses an object frame to represent the information state (capturing the notion of context). This paper presents our framework, the formalism for interaction and dialogue, and an evaluation of the system compared to relevant dialog planning frameworks (i.e. finite state diagrams, frame-based, information state and planning-based dialogue systems).

No associations

LandOfFree

Say what you really think

Search LandOfFree.com for scientists and scientific papers. Rate them and share your experience with other people.

Rating

Domain Directed Dialogs for Decision Processes does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Domain Directed Dialogs for Decision Processes, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Domain Directed Dialogs for Decision Processes will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFWR-SCP-O-363589

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.