Systems and methods for builiding state specific multi-turn contextual language understanding systems

A system with a platform for building a dialog-state specific multi-turn contextual language understanding system for an application, the system comprising:

• at least one processor;
• and
• a memory for storing and encoding computer executable instructions that, when executed by the at least one processor is operative to:
• receive information from a builder for authoring single-shot rules, wherein the information includes any slots and entities necessary for performing a task in one turn of a dialog;
• form the single-shot rules based on the information;
• provide a capability to infer a dialog-state dependent semantic schema for different dialog states based on the single-shot rules and based on user input from a dialog with a user during decoding to form a first provided capability;
• provide a capability to derive dialog-state dependent rules based on the dialog-state dependent semantic schema, the single-shot rules, and the user input from the dialog with the user during the decoding to form a second provided capability;
• and
• implement the single-shot rules, the first provided capability, and the second provided capability to form the dialog-state specific multi-turn contextual language understanding system.

A method for building a dialog-state specific multi-turn contextual language understanding system for an application, the method comprising:

• receiving information from a builder for authoring single-shot rules, wherein the information includes any slots and entities necessary for performing a task in one turn of a dialog;
• forming the single-shot rules based on the information;
• providing a capability to infer a dialog-state dependent semantic schema for different dialog states based on the single-shot rules and based on user input from a dialog with a user during decoding to form a first provided capability;
• providing a capability to derive dialog-state dependent rules based on the dialog-state dependent semantic schema, the single-shot rules, and the user input from the dialog with the user during the decoding to form a second provided capability;
• and
• implementing the single-shot rules, the first provided capability, and the second provided capability to form the dialog-state specific multi-turn contextual language understanding system.