Abstract: A method of processing text within a natural language understanding system can include applying a first tokenization technique to a sentence using a statistical tokenization model. A second tokenization technique using a named entity can be applied to the sentence when the first tokenization technique does not extract a needed token according to a class of the sentence. A token determined according to at least one of the tokenization techniques can be output.

Abstract: The invention disclosed herein concerns a system (100) and method (600) for building a language model representation of an NLU application. The method 500 can include categorizing an NLU application domain (602), classifying a corpus in view of the categorization (604), and training at least one language model in view of the classification (606). The categorization produces a hierarchical tree of categories, sub-categories and end targets across one or more features for interpreting one or more natural language input requests. During development of an NLU application, a developer assigns sentences of the NLU application to categories, sub-categories or end targets across one or more features for associating each sentence with desire interpretations.

Abstract: A method for processing language input can include the step of determining at least two possible meanings for a language input. For each possible meaning, a probability that the possible meaning is a correct interpretation of the language input can be determined. At least one relative data computation can be computed based at least in part upon the probabilities. At least one irregularity within the language input can be detected based upon the relative delta computation. The irregularity can include mumble, ambiguous input, and/or compound input. At least one programmatic action can be performed responsive to the detection of the irregularity.

Abstract: A method for processing language input can include the step of determining at least two possible meanings for a language input. For each possible meaning, a probability that the possible meaning is a correct interpretation of the language input can be determined. At least one relative data computation can be computed based at least in part upon the probabilities. At least one irregularity within the language input can be detected based upon the relative delta computation. The irregularity can include mumble, ambiguous input, and/or compound input. At least one programmatic action can be performed responsive to the detection of the irregularity.

Abstract: A method of classifying text input for use with a natural language understanding system can include determining classification information including a primary classification and one or more secondary classifications for a received text input using a statistical classification model (statistical model). A statistical classification sub-model (statistical sub-model) can be selectively built according to a model generation criterion applied to the classification information. The method further can include selecting the primary classification or the secondary classification for the text input as a final classification according to the statistical sub-model and outputting the final classification for the text input.

Abstract: A method of creating a statistical classification model for a classifier within a natural language understanding system can include processing training data using an existing statistical classification model. Sentences of the training data correctly classified into a selected class of the statistical classification model can be selected. The selected sentences of the training data can be assigned to a fringe group or a core group according to confidence score. The training data can be updated by associating the fringe group with a fringe subclass of the selected class and the core group with a core subclass of the selected class. A new statistical classification model can be built from the updated training data. The new statistical classification model can be output.

Abstract: A method of processing text within a natural language understanding system can include applying a first tokenization technique to a sentence using a statistical tokenization model. A second tokenization technique using a named entity can be applied to the sentence when the first tokenization technique does not extract a needed token according to a class of the sentence. A token determined according to at least one of the tokenization techniques can be output.

Abstract: A method of extracting information from text within a natural language understanding system can include processing a text input through at least one statistical model for each of a plurality of features to be extracted from the text input. For each feature, at least one value can be determined, at least in part, using the statistical model associated with the feature. One value for each feature can be combined to create a complex information target. The complex information target can be output.

Abstract: A method for processing language input can include the step of determining at least two possible meanings for a language input. For each possible meaning, a probability that the possible meaning is a correct interpretation of the language input can be determined. At least one relative data computation can be computed based at least in part upon the probabilities. At least one irregularity within the language input can be detected based upon the relative delta computation. The irregularity can include mumble, ambiguous input, and/or compound input. At least one programmatic action can be performed responsive to the detection of the irregularity.

Abstract: In a natural language, mixed-initiative system, a method of processing user dialogue can include receiving a user input and determining whether the user input specifies an action to be performed or a token of an action. The user input can be selectively routed to an action interpreter or a token interpreter according to the determining step.

Abstract: A method for processing language input can include the step of determining at least two possible meanings for a language input. For each possible meaning, a probability that the possible meaning is a correct interpretation of the language input can be determined. At least one relative data computation can be computed based at least in part upon the probabilities. At least one irregularity within the language input can be detected based upon the relative delta computation. The irregularity can include mumble, ambiguous input, and/or compound input. At least one programmatic action can be performed responsive to the detection of the irregularity.

Abstract: A method and system uses a finite state command grammar coordinated with application scripting to recognize voice command structures for performing an event from an initial location to a new location. The method involves a series of steps, including: recognizing an enabling voice command specifying the event to be performed from the initial location; determining a functional expression for the enabling voice command defined by one or more actions and objects; storing the action and object in a memory location; receiving input specifying the new location; recognizing an activating voice command for performing the event up to the new location; retrieving the stored action and object from the memory location; and performing the event from the initial location to the new location according to the retrieved action and object. Preferably, the enabling-activating command is phrased as “from here . . . to here”.

Abstract: A method for speech enabling labeless controls in an existing graphical user interface can comprise the steps of: identifying controls in a window contained in the graphical user interface; testing each identified control for an associated label; for each identified control having an associated label, adding the associated label to an active grammar of a speech recognition system; for each identified control not having an associated label, creating a label based upon an object property of a contextually relevant user interface object; and, further adding each created label to the active grammar. In testing each identified control for an associated label, an accessibility interface query can be applied to each identified control in the window. In addition, in creating the label, each contextually relevant object can be searched for an object property descriptive of the identified control not having an associated label.

Abstract: A method for speech enabling labeless controls in an existing graphical user interface can comprise the steps of: identifying controls in a window contained in the graphical user interface; testing each identified control for an associated label; for each identified control having an associated label, adding the associated label to an active grammar of a speech recognition system; for each identified control not having an associated label, creating a label based upon an object property of a contextually relevant user interface object; and, further adding each created label to the active grammar. In testing each identified control for an associated label, an accessibility interface query can be applied to each identified control in the window. In addition, in creating the label, each contextually relevant object can be searched for an object property descriptive of the identified control not having an associated label.

Abstract: The method of the invention involves a plurality of steps including, defining a set of user voice commands for hands-free control of a pointer and, in response to receiving a first audio input recognized as one of the set of user voice commands, initiating motion of the pointer in a direction indicated by the user voice command. Subsequently, in response to receiving a second audio input, the pointer motion can be discontinued. Finally, in response to receiving one or more subsequent audio inputs not recognized as being among the set of user voice commands, the pointer can be incrementally moved responsive to the subsequent audio inputs.

Abstract: A method and system uses a finite state command grammar coordinated with application scripting to recognize voice command structures for performing an event from an initial location to a new location. The method involves a series of steps, including: recognizing an enabling voice command specifying the event to be performed from the initial location; determining a functional expression for the enabling voice command defined by one or more actions and objects; storing the action and object in a memory location; receiving input specifying the new location; recognizing an activating voice command for performing the event up to the new location; retrieving the stored action and object from the memory location; and performing the event from the initial location to the new location according to the retrieved action and object. Preferably, the enabling-activating command is phrased as “from here . . . to here”.

Abstract: A method for managing a What Can I Say (WCIS) function in an application having a plurality of commands which can be voice activated comprises the steps of: storing a set of substantially all voice activatable commands associated with the application; identifying those of the commands in the set which are displayable by the application; and, in response to a user input, displaying in a graphical user interface (GUI) a subset of the voice activatable commands which are not displayable by the application. Moreover, the method includes displaying in the GUI, in response to a user input, a list of the stored set of substantially all voice activatable commands associated with the application; displaying in the GUI a pull down menu identifying different categories by which the commands can be viewed in the list; and, displaying the GUI with a pull down menu identifying commands that can be performed against a voice command.

Abstract: A method for displaying voice commands with multiple variables in a speech application, comprises the steps of: compiling a list of each voice command which can include at least one variable; storing with each the voice command each variable associated with each voice the command in the list; displaying in response to a user request a command and each of its associated variables; and, displaying each of the associated variables within delimiters to indicate to the user that a choice must be made from a set of choices for each the associated variable together with the command. A set of choices for each stored variable can be stored. The set of the choices for each variable associated with the voice command and at least one word to use to select one of the choices in each the set when uttering the voice command can be supplied in response to a user request.