Abstract: Techniques for performing centralized unsuperivised learning in a multi-domain system are described. A user may request labeled data for an ML task, where the request includes a prompt for obtaining relevant explicit user feedback. The system may use the prompt to collect explicit user feedback for relevant runtime user inputs. After a duration of time (in the user's request for labeled data) has elapsed, the system determines whether collected user feedback indicates processing of the user input was defective and, if so, determines a cause of the defective processing. The system then uses one or more label generators to generate labeled data using the collected user feedback, whether the processing was defective, and the determined defect cause.

Abstract: Techniques for presenting an alternative input representation to a user for testing and collecting processing data are described. A system may determine that a received spoken input triggers an alternative input representation for presenting. The system may output data corresponding to the alternative input representation in response to the received spoken input, and the system may receive user feedback from the user. The system may store the user feedback and processing data corresponding to processing of the alternative input representation, which may be later used to update an alternative input component configured to determine alternative input representations for spoken inputs.

Abstract: Techniques for decreasing (or eliminating) the possibility of a skill performing an action that is not responsive to a corresponding user input are described. A system may train one or more machine learning models with respect to user inputs, which resulted in incorrect actions being performed by skills, and corresponding user inputs, which resulted in the correct action being performed. The system may use the trained machine learning model(s) to rewrite user inputs that, if not rewritten, may result in incorrect actions being performed. The system may implement the trained machine learning model(s) with respect to ASR output text data to determine if the ASR output text data corresponds (or substantially corresponds) to previous ASR output text data that resulted in an incorrect action being performed.

Abstract: Techniques for determining and using interaction affinity data are described. Interaction affinity data may indicate a latent affinity between information corresponding to an interaction, such as, intents, entities, device type from which a user input is received, domain, etc. A system may use the interaction affinity data to determine an alternative input representation for a spoken input to cause output of a desired response to the spoken input. The system may also use the interaction affinity data to recommend an action to a user.

Abstract: Techniques for determining an intent for a user input in a dialog are described. The system processes historic interaction data that is structured based skills and intents, with each skill-intent pair being associated with one or more past user inputs received by the system, one or more sample inputs, and one or more alternative representations of the user inputs. Based on processing of the historic interaction data and dialog data of previous turns of the dialog, the system determines potential intents for the user input of the current turn of the dialog. The potential intents may correspond to a presently active skill or another skill, enabling the user to interact with another skill during the dialog.

Abstract: Described herein is a system for responding to a frustrated user with a response determined based on spoken language understanding (SLU) processing of a user input. The system detects user frustration and responds to a repeated user input by confirming an action to be performed or presenting an alternative action, instead of performing the action responsive to the user input. The system also detects poor audio quality of the captured user input, and responds by requesting the user to repeat the user input. The system processes sentiment data and signal quality data to respond to user inputs.

Abstract: Techniques for handling errors during processing of natural language inputs are described. A system may process a natural language input to generate an ASR hypothesis or NLU hypothesis. The system may use more than one data searching technique (e.g., deep neural network searching, convolutional neural network searching, etc.) to generate an alternate ASR hypothesis or NLU hypothesis, depending on the type of hypothesis input for alternate hypothesis processing.

Abstract: A system is provided for reducing friction during user interactions with a natural language processing system, such as voice assistant systems. The system determines a pre-trained model using dialog session data corresponding to multiple user profiles. The system determines a fine-tuned model using the pre-trained model and a fine-tuning dataset that corresponds to a particular task, such as query rewriting. The system uses the fine-tuned model to process a user input and determine an alternative representation of the input that can result in a desired response from the natural language processing system.

Abstract: A system is provided for a self-learning policy engine that can be used by various spoken language understanding (SLU) processing components. The system also provides for sharing contextual information from processing performed by an upstream SLU component to a downstream SLU component to facilitate decision making by the downstream SLU component. The system also provides for a SLU component to select from a variety of actions to take. A SLU component may implement an instance of the self-learning policy that is specifically configured for the particular SLU component.

Abstract: Techniques for determining an intent of a subsequent user input in a dialog are described. The system processes historic interaction data that is structured based on natural language understanding (NLU) hypotheses, with each NLU hypothesis being associated with one or more past user inputs received by the system, one or more sample inputs, and one or more past system responses. Based on processing of the historic interaction data and dialog data of previous turns of the dialog, the system determines candidate intents for the subsequent turn of the dialog. The system also uses context data to determine the candidate intents.

Abstract: Described herein is a system for responding to a frustrated user with a response determined based on spoken language understanding (SLU) processing of a user input. The system detects user frustration and responds to a repeated user input by confirming an action to be performed or presenting an alternative action, instead of performing the action responsive to the user input. The system also detects poor audio quality of the captured user input, and responds by requesting the user to repeat the user input. The system processes sentiment data and signal quality data to respond to user inputs.

Abstract: Techniques for handling errors during processing of natural language inputs are described. A system may process a natural language input to generate an ASR hypothesis or NLU hypothesis. The system may use more than one data searching technique (e.g., deep neural network searching, convolutional neural network searching, etc.) to generate an alternate ASR hypothesis or NLU hypothesis, depending on the type of hypothesis input for alternate hypothesis processing.

Abstract: A system is provided for handling errors during automatic speech recognition by leveraging past inputs spoken by the user. The system may process a user input to determine an ASR hypothesis. The system may then determine an alternate representation of the user input based on the inputs provided by the user in the past, and whether the ASR hypothesis sufficiently matches one of the past inputs.

Abstract: A system is provided for a self-learning policy engine that can be used by various spoken language understanding (SLU) processing components. The system also provides for sharing contextual information from processing performed by an upstream SLU component to a downstream SLU component to facilitate decision making by the downstream SLU component. The system also provides for a SLU component to select from a variety of actions to take. A SLU component may implement an instance of the self-learning policy that is specifically configured for the particular SLU component.

Abstract: A system is provided for reducing friction during user interactions with a natural language processing system, such as voice assistant systems. The system determines a pre-trained model using dialog session data corresponding to multiple user profiles. The system determines a fine-tuned model using the pre-trained model and a fine-tuning dataset that corresponds to a particular task, such as query rewriting. The system uses the fine-tuned model to process a user input and determine an alternative representation of the input that can result in a desired response from the natural language processing system.

Abstract: A system is provided for handling errors during automatic speech recognition by processing a potentially defective utterance to determine an alternative, potentially successful utterance. The system processes an ASR hypothesis, using a probabilistic graph, to determine a likelihood that it will result in an error. Using the probabilistic graph, the system determines an alternate utterance.

Abstract: Techniques for decreasing (or eliminating) the possibility of a skill performing an action that is not responsive to a corresponding user input are described. A system may train one or more machine learning models with respect to user inputs, which resulted in incorrect actions being performed by skills, and corresponding user inputs, which resulted in the correct action being performed. The system may use the trained machine learning model(s) to rewrite user inputs that, if not rewritten, may result in incorrect actions being performed. The system may implement the trained machine learning model(s) with respect to ASR output text data to determine if the ASR output text data corresponds (or substantially corresponds) to previous ASR output text data that resulted in an incorrect action being performed.

Abstract: Systems and methods are disclosed to provide optimized scheduling of calendar events based on flexibility scores of calendar events. A flexibility score may be representative of a probability or likelihood that a calendar event can or will be rescheduled in response to a conflicting calendar event. Flexibility scores of calendar events may be calculated based on one or more factors, which may be weighted, using one or more machine-learning models. Factors may include: event densities of invitees' calendars, organizational rankings of respective invitees, the remaining time before an event start time, an urgency of respective calendar events, etc. In this way, if open time slots are not available for all invitees to a proposed calendar request, an event organizer may identify time slots occupied by existing calendar events with the highest likelihood of being rescheduled in view of the proposed calendar event, thereby facilitating scheduling of the proposed calendar event.

Abstract: Described herein is a system for prompting a user for clarification when an automatic speech recognition (ASR) system encounters ambiguity with respect to the user's input. The feedback provided by the user is used to retrain machine-learning models and/or to generate new machine-learning models. Based on the type of ambiguity, the system may determine to retrain one or more ASR models that are widely used by the system or to generate/update one or more user-specific models that are used to process inputs from one or more particular users.

Abstract: Described herein is a system for responding to a frustrated user with a response determined based on spoken language understanding (SLU) processing of a user input. The system detects user frustration and responds to a repeated user input by confirming an action to be performed or presenting an alternative action, instead of performing the action responsive to the user input. The system also detects poor audio quality of the captured user input, and responds by requesting the user to repeat the user input. The system processes sentiment data and signal quality data to respond to user inputs.