Abstract: Techniques for determining a command or intent likely to be subsequently invoked by a user of a system are described. A user inputs a command (either via a spoken utterance or textual input) to a system. The system determines content responsive to the command. The system also determines a second command or corresponding intent likely to be invoked by the user subsequent to the previous command. Such determination may involve analyzing pairs of intents, with each pair being associated with a probability that one intent of the pair will be invoked by a user subsequent to a second intent of the pair. The system then outputs first content responsive to the first command and second content soliciting the user as to whether the system to execute the second command.

Abstract: Techniques for limiting natural language processing performed on input data are described. A system receives input data from a device. The input data corresponds to a command to be executed by the system. The system determines applications likely configured to execute the command. The system performs named entity recognition and intent classification with respect to only the applications likely configured to execute the command.

Abstract: Systems and methods for building conversational understanding systems are provided. More specifically, the systems and methods utilize prebuilt conversational items that can form a CU system upon selection by a builder without requiring any further input from the builder. Accordingly, the systems and methods for building a conversational understanding system reduce the expertise, time, and resources necessary to build a conversational understanding system for an application when compared to systems and methods that utilize conversational items that require further input from the builder.

Abstract: Aspects herein provide third-party application authors with a resolver chaining platform that simplifies the task of creating customized resolvers to gather information from user input while also allowing those authors to chain their custom resolvers with generic resolvers provided by the platform's host and that relate to commonly used parameter types. In particular, the present disclosure provides a method and system for authoring and using these resolver chains made up of a combination of custom and generic resolvers.

Abstract: A computer-implemented technique is described for facilitating the creation of a language understanding (LU) component for use with an application. The technique allows a developer to select a subset of parameters from a larger set of parameters. The subset of parameters pertains to a LU scenario to be handled by the application. The larger set of parameters pertains to a plurality of LU scenarios handled by an already-existing generic LU model. The technique creates a constrained LU component that is based on the subset of parameters in conjunction with the generic LU model. At runtime, the constrained LU component interprets input language items using the generic LU model in a manner that is constrained by the subset of parameters that have been selected, to provide an output result. The technique also allows the developer to create new rules and/or supplemental models.

Abstract: Systems, components, devices, and methods for resolving ambiguity in a conversational understanding system are provided. A non-limiting example is a system or method for resolving ambiguity in a conversational understanding system. The method includes the steps of receiving a natural language input and identifying an agent action based on the natural language input. The method also includes the steps of determining an ambiguity value associated with the agent action and evaluating the ambiguity value against an ambiguity condition. The method includes the steps of when determined that the ambiguity value meets the ambiguity condition: selecting a prompting action based on the ambiguity associated with the identified agent action, performing the prompting action, receiving additional input in response to the prompting action, and updating the agent action to resolve the ambiguity based on the additional input. The method also includes the step of performing the agent action.

Abstract: Multi-turn cross-domain natural language understanding (NLU) systems and platforms for building the multi-turn cross-domain NLU system are provided. Further, methods for using and building the multi-turn cross-domain NLU system are provided. More specifically, the multi-turn cross-domain NLU system supports multi-turn bot/agent/application scenarios for new domains without having to select a task definition and/or define a new schema during the building of the NLU system. Accordingly, the platform for building the multi-turn cross-domain NLU system that does not require the builder to select a task and/or build a schema for a selected task provides an easy to use, cost effective, and efficient service for building a NLU system. Further, the multi-turn cross-domain NLU system provides a more versatile NLU system than previously utilized NLU systems that were trained for and limited to a selected task and/or domain.

Abstract: A computer-implemented technique is described herein for training a personal digital assistant (PDA) component and a simulated user (SU) component via a self-learning strategy. The technique involves conducting interactions between the PDA component and the SU component over the course of plural dialogs, and with respect to plural tasks. These interactions yield training data. A training system uses the training data to generate and update analysis components used by both the PDA component and the SU component. According to one illustrative aspect, the SU component is configured to mimic the behavior of actual users, across a range of different user types.

Abstract: A computer-implemented technique is described for facilitating the creation of a language understanding (LU) component for use with an application. The technique allows a developer to select a subset of parameters from a larger set of parameters. The subset of parameters pertains to a LU scenario to be handled by the application. The larger set of parameters pertains to a plurality of LU scenarios handled by an already-existing generic LU model. The technique creates a constrained LU component that is based on the subset of parameters in conjunction with the generic LU model. At runtime, the constrained LU component interprets input language items using the generic LU model in a manner that is constrained by the subset of parameters that have been selected, to provide an output result. The technique also allows the developer to create new rules and/or supplemental models.

Abstract: Techniques for determining a command or intent likely to be subsequently invoked by a user of a system are described. A user inputs a command (either via a spoken utterance or textual input) to a system. The system determines content responsive to the command. The system also determines a second command or corresponding intent likely to be invoked by the user subsequent to the previous command. Such determination may involve analyzing pairs of intents, with each pair being associated with a probability that one intent of the pair will be invoked by a user subsequent to a second intent of the pair. The system then outputs first content responsive to the first command and second content soliciting the user as to whether the system to execute the second command.

Abstract: A canonicalizer can be used with or implemented within a natural language understanding (NLU) component of a speech processing system to enable the system to properly identify an entity to which a user refers in a spoken utterance. The canonicalizer may determine a first canonical value using a gazetteer associated with a determined intent of the spoken utterance. The canonicalizer may determine a second canonical value using a look-up table of canonical values. The canonicalizer may then output either the first canonical value or the second canonical value for further NLU processing, such as entity resolution.

Abstract: Multi-turn cross-domain natural language understanding (NLU) systems and platforms for building the multi-turn cross-domain NLU system are provided. Further, methods for using and building the multi-turn cross-domain NLU system are provided. More specifically, the multi-turn cross-domain NLU system supports multi-turn bot/agent/application scenarios for new domains without having to select a task definition and/or define a new schema during the building of the NLU system. Accordingly, the platform for building the multi-turn cross-domain NLU system that does not require the builder to select a task and/or build a schema for a selected task provides an easy to use, cost effective, and efficient service for building a NLU system. Further, the multi-turn cross-domain NLU system provides a more versatile NLU system than previously utilized NLU systems that were trained for and limited to a selected task and/or domain.

Abstract: Non-limiting examples of the present disclosure describe decoupling task state tracking that is managed by a shared task completion platform from execution of tasks by a task resource owner. Task registration data is received at a shared task state platform for a task that is executable by a task owner resource. Task registration data comprises parameters to be collected for execution of the task and ancillary information, such as the name of the task and whether to confirm the values of the parameters after collection. During interaction with a user, the shared task completion platform receives an input and determines the task is associated with the received input. During the interaction, parameters of the received task registration data are utilized to collect data for execution of the task. The collected data is transmitted to the task owner resource for execution of the task.

Abstract: Non-limiting examples of the present disclosure describe generation and application of a universal hypothesis ranking model to rank/re-re-rank dialog hypotheses. An input is received through a user interface of an application for dialog processing. A plurality of dialog hypotheses are generated based on input understanding processing of the received input. The plurality of dialog hypotheses are ranked using a universal hypothesis ranking model that is applicable to a plurality of languages and locales. The ranking of the plurality of dialog hypotheses comprises using the universal hypothesis ranking model to analyze language independent features of the plurality of dialog hypotheses for policy determination. Other examples are also described including examples directed to generation of the universal hypothesis ranking model.

Abstract: Environmental conditions, along with other information, are used to adjust a response of a conversational dialog system. The environmental conditions may be used at different times within the conversational dialog system. For example, the environmental conditions can be used to adjust the dialog manager's output (e.g., the machine action). The dialog state information that is used by the dialog manager includes environmental conditions for the current turn in the dialog as well as environmental conditions for one or more past turns in the dialog. The environmental conditions can also be used after receiving the machine action to adjust the response that is provided to the user. For example, the environmental conditions may affect the machine action that is determined as well as how the action is provided to the user. The dialog manager and the response generation components in the conversational dialog system each use the available environmental conditions.

Abstract: Examples of the present disclosure describe processing by an input understanding system/service. A received input is processed to generate a set of alternatives for recognizing the received input. The set of alternatives is filtered. Filtering comprises ranking the set of alternatives and propagating a plurality of the ranked alternatives for additional processing. The propagated alternatives are processed to generate an expanded set of alternatives for potential hypotheses based on the received input. The expanded set of alternatives is filtered. Filtering comprises ranking alternatives of the expanded set and propagating a plurality of the ranked alternatives of the expanded set for additional processing. The propagated alternatives of the expanded set are evaluated based on application of knowledge data fetched from external resources. A response to the received input is generated.

Abstract: A computer-implemented technique is described for processing a linguistic item (e.g., a query) in an efficient and scalable manner. The technique interprets the linguistic item using a language understanding (LU) system in a manner that is based on a particular endpoint mechanism from which the linguistic item originated. The LU system may include an endpoint-independent subsystem, an endpoint-dependent subsystem, and a ranking component. The endpoint-independent subsystem interprets the linguistic item in a manner that is independent of the particular endpoint mechanism. The endpoint-dependent subsystem interprets the linguistic item in a manner that is dependent on the particular endpoint mechanism. The ranking component generates final interpretation results based on intermediate results generated by the endpoint-independent subsystem and the endpoint-dependent subsystem, e.g., by identifying the most likely interpretation of the linguistic item.

Abstract: Systems and methods for augmenting existing CU system to be used with content, such as a website. The content may be parsed to determine on or more actions that may be performed by a user who uses the content. These actions may then be compared to tasks of CU systems to identify potential matches. When a match is found, the CU system may be updated to include information.

Abstract: Aspects of the present invention provide a technique to validate the transfer of intents or entities between existing natural language model domains (hereafter “domain” or “NLU”) using click logs, a knowledge graph, or both. At least two different types of transfers are possible. Intents from a first domain may be transferred to a second domain. Alternatively or additionally, entities from the second domain may be transferred to an existing intent in the first domain. Either way, additional intent/entity pairs can be generated and validated. Before the new intent/entity pair is added to a domain, aspects of the present invention validate that the intent or entity is transferable between domains. Validation techniques that are consistent with aspects of the invention can use a knowledge graph, search query click logs, or both to validate a transfer of intents or entities from one domain to another.

Abstract: In language evaluation systems, user expressions are often evaluated by speech recognizers and language parsers, and among several possible translations, a highest-probability translation is selected and added to a dialog sequence. However, such systems may exhibit inadequacies by discarding alternative translations that may initially exhibit a lower probability, but that may have a higher probability when evaluated in the full context of the dialog, including subsequent expressions. Presented herein are techniques for communicating with a user by formulating a dialog hypothesis set identifying hypothesis probabilities for a set of dialog hypotheses, using generative and/or discriminative models, and repeatedly re-ranks the dialog hypotheses based on subsequent expressions.