Abstract: A processing unit can train a model as a joint multi-domain recurrent neural network (JRNN), such as a bi-directional recurrent neural network (bRNN) and/or a recurrent neural network with long-short term memory (RNN-LSTM) for spoken language understanding (SLU). The processing unit can use the trained model to, e.g., jointly model slot filling, intent determination, and domain classification. The joint multi-domain model described herein can estimate a complete semantic frame per query, and the joint multi-domain model enables multi-task deep learning leveraging the data from multiple domains. The joint multi-domain recurrent neural (JRNN) can leverage semantic intents (such as, finding or identifying, e.g., a domain specific goal) and slots (such as, dates, times, locations, subjects, etc.) across multiple domains.

Abstract: A processing unit can train a model as a joint multi-domain recurrent neural network (JRNN), such as a bi-directional recurrent neural network (bRNN) and/or a recurrent neural network with long-short term memory (RNN-LSTM) for spoken language understanding (SLU). The processing unit can use the trained model to, e.g., jointly model slot filling, intent determination, and domain classification. The joint multi-domain model described herein can estimate a complete semantic frame per query, and the joint multi-domain model enables multi-task deep learning leveraging the data from multiple domains. The joint multi-domain recurrent neural network (JRNN) can leverage semantic intents (such as, finding or identifying, e.g., a domain specific goal) and slots (such as, dates, times, locations, subjects, etc.) across multiple domains.

Abstract: A processing unit can extract salient semantics to model knowledge carryover, from one turn to the next, in multi-turn conversations. Architecture described herein can use the end-to-end memory networks to encode inputs, e.g., utterances, with intents and slots, which can be stored as embeddings in memory, and in decoding the architecture can exploit latent contextual information from memory, e.g., demographic context, visual context, semantic context, etc. e.g., via an attention model, to leverage previously stored semantics for semantic parsing, e.g., for joint intent prediction and slot tagging. In examples, architecture is configured to build an end-to-end memory network model for contextual, e.g., multi-turn, language understanding, to apply the end-to-end memory network model to multiple turns of conversational input; and to fill slots for output of contextual, e.g., multi-turn, language understanding of the conversational input.

Abstract: A network computer system for managing a network service (e.g., a transport service) can include a voice-assistant subsystem for generating dialogues and performing actions for service providers of the network service. The network computer system can receive, from a user device, a request for the network service. In response, the network computer system can identify a service provider and transmit an invitation to the provider device of the service provider. In response to the identification of the service provider for the request, the voice-assistant subsystem can trigger an audio voice prompt to be presented on the provider device and a listening period during which the provider device monitors for an audio input from the service provider. Based on the audio input captured by the provider device, the network computer system can determine an intent corresponding to whether the service provider accepts or declines the invitation.

Abstract: A network computer system for managing a network service (e.g., a transport service) can include a voice-assistant subsystem for generating dialogues and performing actions for service providers of the network service. The network computer system can receive, from a user device, a request for the network service. In response, the network computer system can identify a service provider and transmit an invitation to the provider device of the service provider. In response to the identification of the service provider for the request, the voice-assistant subsystem can trigger an audio voice prompt to be presented on the provider device and a listening period during which the provider device monitors for an audio input from the service provider. Based on the audio input captured by the provider device, the network computer system can determine an intent corresponding to whether the service provider accepts or declines the invitation.

Abstract: Devices and techniques are generally described for learning personalized responses to declarative natural language inputs. In various examples, a first natural language input may be received. The first natural language input may correspond to intent data corresponding to a declarative user input. In some examples, a dialog session may be initiated with the first user. An action intended by the first user for the first natural language input may be determined based at least in part on the dialog session. In various examples, first data representing the action may be stored in association with second data representing a state described by at least a portion of the first natural language input.

Abstract: Natural language query translation may be provided. A statistical model may be trained to detect domains according to a plurality of query click log data. Upon receiving a natural language query, the statistical model may be used to translate the natural language query into an action. The action may then be performed and at least one result associated with performing the action may be provided.

Abstract: Systems and methods for determining knowledge-guided information for a recurrent neural networks (RNN) to guide the RNN in semantic tagging of an input phrase are presented. A knowledge encoding module of a Knowledge-Guided Structural Attention Process (K-SAP) receives an input phrase and, in conjunction with additional sub-components or cooperative components generates a knowledge-guided vector that is provided with the input phrase to the RNN for linguistic semantic tagging. Generating the knowledge-guided vector comprises at least parsing the input phrase and generating a corresponding hierarchical linguistic structure comprising one or more discrete sub-structures. The sub-structures may be encoded into vectors along with attention weighting identifying those sub-structures that have greater importance in determining the semantic meaning of the input phrase.

Abstract: A method for assisting a user with one or more desired tasks is disclosed. For example, an executable, generic language understanding module and an executable, generic task reasoning module are provided for execution in the computer processing system. A set of run-time specifications is provided to the generic language understanding module and the generic task reasoning module, comprising one or more models specific to a domain. A language input is then received from a user, an intention of the user is determined with respect to one or more desired tasks, and the user is assisted with the one or more desired tasks, in accordance with the intention of the user.

Abstract: A network computer system for managing a network service (e.g., a transport service) can include a voice-assistant subsystem for generating dialogues and performing actions for service providers of the network service. The network computer system can receive, from a user device, a request for the network service. In response, the network computer system can identify a service provider and transmit an invitation to the provider device of the service provider. In response to the identification of the service provider for the request, the voice-assistant subsystem can trigger an audio voice prompt to be presented on the provider device and a listening period during which the provider device monitors for an audio input from the service provider. Based on the audio input captured by the provider device, the network computer system can determine an intent corresponding to whether the service provider accepts or declines the invitation.

Abstract: Systems and methods for determining knowledge-guided information for a recurrent neural networks (RNN) to guide the RNN in semantic tagging of an input phrase are presented. A knowledge encoding module of a Knowledge-Guided Structural Attention Process (K-SAP) receives an input phrase and, in conjunction with additional sub-components or cooperative components generates a knowledge-guided vector that is provided with the input phrase to the RNN for linguistic semantic tagging. Generating the knowledge-guided vector comprises at least parsing the input phrase and generating a corresponding hierarchical linguistic structure comprising one or more discrete sub-structures. The sub-structures may be encoded into vectors along with attention weighting identifying those sub-structures that have greater importance in determining the semantic meaning of the input phrase.

Abstract: The present invention relates to a method and apparatus for exploiting human feedback in an intelligent automated assistant. One embodiment of a method for conducting an interaction with a human user includes inferring an intent from data entered by the human user, formulating a response in accordance with the intent, receiving feedback from a human advisor in response to at least one of the inferring and the formulating, wherein the human advisor is a person other than the human user, and adapting at least one model used in at least one of the inferring and the formulating, wherein the adapting is based on the feedback.

Abstract: Systems and methods for determining knowledge-guided information for a recurrent neural networks (RNN) to guide the RNN in semantic tagging of an input phrase are presented. A knowledge encoding module of a Knowledge-Guided Structural Attention Process (K-SAP) receives an input phrase and, in conjunction with additional sub-components or cooperative components generates a knowledge-guided vector that is provided with the input phrase to the RNN for linguistic semantic tagging. Generating the knowledge-guided vector comprises at least parsing the input phrase and generating a corresponding hierarchical linguistic structure comprising one or more discrete sub-structures. The sub-structures may be encoded into vectors along with attention weighting identifying those sub-structures that have greater importance in determining the semantic meaning of the input phrase.

Abstract: A method for assisting a user with one or more desired tasks is disclosed. For example, an executable, generic language understanding module and an executable, generic task reasoning module are provided for execution in the computer processing system. A set of run-time specifications is provided to the generic language understanding module and the generic task reasoning module, comprising one or more models specific to a domain. A language input is then received from a user, an intention of the user is determined with respect to one or more desired tasks, and the user is assisted with the one or more desired tasks, in accordance with the intention of the user.

Abstract: Structured web pages are accessed and parsed to obtain implicit annotation for natural language understanding tasks. Search queries that hit these structured web pages are automatically mined for information that is used to semantically annotate the queries. The automatically annotated queries may be used for automatically building statistical unsupervised slot filling models without using a semantic annotation guideline. For example, tags that are located on a structured web page that are associated with the search query may be used to annotate the query. The mined search queries may be filtered to create a set of queries that is in a form of a natural language query and/or remove queries that are difficult to parse. A natural language model may be trained using the resulting mined queries. Some queries may be set aside for testing and the model may be adapted using in-domain sentences that are not annotated.

Abstract: A machine-readable medium may include a group of reusable components for building a spoken dialog system. The reusable components may include a group of previously collected audible utterances. A machine-implemented method to build a library of reusable components for use in building a natural language spoken dialog system may include storing a dataset in a database. The dataset may include a group of reusable components for building a spoken dialog system. The reusable components may further include a group of previously collected audible utterances. A second method may include storing at least one set of data. Each one of the at least one set of data may include ones of the reusable components associated with audible data collected during a different collection phase.

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: A dialog system for use in a multi-user, multi-domain environment. The dialog system understands user requests when multiple users are interacting with each other as well as the dialog system. The dialog system uses multi-human conversational context to improve domain detection. Using interactions between multiple users allows the dialog system to better interpret machine directed conversational inputs in multi-user conversational systems. The dialog system employs topic segmentation to chunk conversations for determining context boundaries. Using general topic segmentation methods, as well as the specific domain detector trained with conversational inputs collected by a single user system, allows the dialog system to better determine the relevant context. The use of conversational context helps reduce the domain detection error rate, especially in certain domains, and allows for better interactions with users when the machine addressed turns are not recognized or are ambiguous.

Abstract: A method for assisting a user with one or more desired tasks is disclosed. For example, an executable, generic language understanding module and an executable, generic task reasoning module are provided for execution in the computer processing system. A set of run-time specifications is provided to the generic language understanding module and the generic task reasoning module, comprising one or more models specific to a domain. A language input is then received from a user, an intention of the user is determined with respect to one or more desired tasks, and the user is assisted with the one or more desired tasks, in accordance with the intention of the user.

Abstract: An apparatus and a method for preserving privacy in natural language databases are provided. Natural language input may be received. At least one of sanitizing or anonymizing the natural language input may be performed to form a clean output. The clean output may be stored.