Abstract:
A system and method for providing conversational computing via a protocol for automatic dialog management and arbitration between a plurality of conversational applications, and a framework for supporting such protocol, in a multi-modal and/or multi-channel environment. A DMAF (dialog manager and arbitrator facade) interfaces with one or more applications, and a hierarchical DMA architecture enables arbitration across the applications and within the same application between various sub-dialogs.
Abstract:
PROBLEM TO BE SOLVED: To provide a device for automatically discriminating a command boundary in a conversation type natural language system. SOLUTION: This device comprises a voice recognizing device 20 for converting an input signal into a recognized text 30 and a boundary discriminating device 40 connected to the voice recognizing device 20 to receive the recognized text 30 and determine whether a command is present in the recognized text 30 or not. The boundary discriminating device 40 outputs the command when the command is present in the recognized text 30. The method for discriminating a command boundary in a conversation type natural language system is also included.
Abstract:
A method of translating a natural language input 10 into a formal computer command 14 comprises the steps of translating the input command into a category at a first translation level 102 with a further translation at a second level 102 associated with the category. Further translation may occur at additional levels as determined by the preceding translation level. Preferably a plurality of models 212 will be provided at each level, each model being associated with a category and comprising a subset of formal commands. Preferably the formal command 14 will be applied to an application 16. In this instance the first level categories can be associated with the application, the second and subsequent levels being associated with specific application functions.. In a second embodiment probability scoring 214 may be used to determine which category should be used at the next level of translation where at least two possible candidate categories have been identified.. A method of building the category models is also claimed.
Abstract:
Apparatus for automatically identifying command boundaries in a conversational natural language system includes a speech recognizer 20 for converting an input signal to recognized text and a boundary identifier 40 receiving the recognized text and determining if a command is present in the recognized text, the boundary identifier outputting the command if present in the recognized text.
Abstract:
In accordance with the invention, a method and system for accessing a dialog system 101 employing a plurality of different clients 100, includes providing a first client device for accessing a conversational system 300 and presenting a command to the conversational system 300 by converting the command to a form understandable to the conversational system. The command is interpreted by employing a mediator 302, a dialog manager 303 and a multi-modal history 304 to determine the intent of the command based on a context of the command. A second client device is determined based on a predetermined device preference stored in the conversational system. An application is abstracted (400) to perform the command, and the results of the performance of the command are sent to the second client device.
Abstract:
A method and system, which may be implemented by employing a program, perform method steps of a natural language understanding (NLU) system which include tagging, 200, recognized words of a command input to the NLU system to associate the command with a context, and translating, 300, the command to at least one formal command based on the tagged words. A top ranked formal command is determined, 400, based on scoring of the tagged recognized words and scoring translations of the at least one formal command. Whether the top ranked formal command is accepted is determined by comparing a feature vector of the top ranked formal command to representations of feature vectors stored in an accept model. The top ranked formal command is executed, 500, if accepted and incorrect commands are prevented from execution.
Abstract:
A method for hierarchical translation of input to a formal command in natural language understanding systems includes presenting an input command to be translated to a natural language understanding engine. At least two translator levels are provided in the natural language understanding engine. A first translator level of the at least two translator levels translates the input command into at least one category by associating the input command with the at least one category for the next level of translators. A formal language command is output for the input command from a last of the at least two translator levels based on the input command and the at least one category.
Abstract:
A method for determining and maintaining dialog focus in a conversational speech system includes presenting a command associated with an application to a dialog manager 14. The application associated with the command is unknown to the dialog manager at the time it is made. The dialog manager 14 determines a current context of the command by reviewing a multi-modal history of event 16. At least one method is determined responsive to the command based on the current context. The at least one method is executed responsive to the command associated with the application.