Method, system, and apparatus for natural language mixed-initiative dialogue processing

1. In a natural language, mixed-initiative system, a method of processing user dialogue comprising the steps of:

receiving user inputs at a main menu detector, the main menu detector determining whether the user input specifies an action to be performed or a token of information for an action, wherein user inputs specifying context dependent data are routed to the main menu detector by a classifier configured to distinguish user inputs specifying context dependent data from user inputs specifying context independent data, and wherein the classifier routes user inputs specifying context independent data to an action interpreter;

for a user input determined by the main menu detector to be an action, routing the user input to the action interpreter; and

for a user input determined to be a token, routing the user input to an action router that routes the user input to one of a plurality of token interpreters that is determined by the action router to be suited for interpreting the user input.

2. The method of claim 1 , further comprising:

classifying a token determined from the user input if the user input is determined to be a token; and

routing the token to one of a plurality of token interpreters according to said classifying step.

3. The method of claim 2 , wherein the classifying step identifies the token according to an action identified by the system, an action corresponding to a current state of a system, a category of the user input, a particular domain, or sub-domain.

4. In a natural language, mixed-initiative system, a method of processing user dialogue comprising the steps of:

receiving at a main menu detector a first user input specifying an action, wherein user inputs specifying context dependent data are routed to the main menu detector by a classifier configured to distinguish user inputs specifying context dependent data from user inputs specifying context independent data, and wherein the classifier routes user inputs specifying context independent data to an action interpreter;

routing said first user input to an action interpreter configured to determine an action from received user input and to provide the action to an action router;

receiving a second user input;

determining whether the second user input specifies an action or a token corresponding to an action; and

providing the second user input to the processor configured to determine an action or to a processor configured to determine a token from received user input according to said determining step.

5. The method of claim 4 , further comprising the step of performing the action specified by the first user input.

6. The method of claim 4 , further comprising the step of determining that the second user input specifies a second action to be performed.

7. The method of claim 4 , further comprising the steps of, after said step of providing the first user input to a processor, determining that a token is required to perform the action specified by the first user input and querying the user for the token.