We present a prototype natural-language problem-solving application for a financial services call center, developed as part of the Amitiés multilingual human-computer dialogue project. Our automated dialogue system, based on empirical evidence from real call-center conversations, features a datadriven approach that allows for mixed system/customer initiative and spontaneous conversation. Preliminary evaluation results indicate efficient dialogues and high user satisfaction, with performance comparable to or better than that of current conversational travel information systems.

No abstract

Dialog participants in a non-mixed initiative dialogs, in which one participant asks questions exclusively and the other participant responds to those questions exclusively, can select actions that minimize the expected length of the dialog. The choice of question that minimizes the expected number of questions to be asked can be computed in polynomial time in some cases. The polynomial-time solutions to special cases of the problem suggest a number of strategies for selecting dialog actions in the intractable general case. In a simulation involving 1000 dialog scenarios, an approximate solution using the most probable rule set/least probable question resulted in expected dialog length of 3.60 questions per dialog, as compared to 2.80 for the optimal case, and 5.05 for a randomly chosen strategy.

No abstract

No abstract