Abstract: Systems and processes for operating a virtual assistant programmed to refer to shared domain concepts using concept nodes are provided. An example process includes receiving a user speech input, determining a primary domain corresponding to a textual representation of the user speech input, identifying, from the textual representation, a first substring that corresponds to a first concept of the primary domain, parsing the first substring to determine a secondary domain of the plurality of domains, and based on the secondary domain, obtaining a data item corresponding to the first substring. In accordance with determining that the data item is valid for resolving the first concept of the primary domain, extracting, from the data item, a parameter value for the first concept of the primary domain and invoking a service based on the primary domain to produce a result using the parameter value for the first concept.

Abstract: Systems and processes for natural language processing using vocabularies with compressed serialized tries are described in the present disclosure. In one example process, natural language input is received. The natural language input is parsed, using a vocabulary, to determine a corresponding user intent. The parsing includes using a data structure of the vocabulary to map a first word of the natural language input to first semantic information and a second word of the natural language input to second semantic information. The data structure includes pointers that map to a same semantic data object of the vocabulary. The first semantic information and the second semantic information are determined using the same semantic data object. The user intent is determined based on the first semantic information and the second semantic information. Performance of a task corresponding to the determined user intent is initiated.

Abstract: Systems and processes for natural language processing using vocabularies with compressed serialized tries are described in the present disclosure. In one example process, natural language input is received. The natural language input is parsed, using a vocabulary, to determine a corresponding user intent. The parsing includes using a data structure of the vocabulary to map a first word of the natural language input to first semantic information and a second word of the natural language input to second semantic information. The data structure includes pointers that map to a same semantic data object of the vocabulary. The first semantic information and the second semantic information are determined using the same semantic data object. The user intent is determined based on the first semantic information and the second semantic information. Performance of a task corresponding to the determined user intent is initiated.

Abstract: Systems and processes for operating a virtual assistant programmed to refer to shared domain concepts using concept nodes are provided. In an example process, user speech input is received. A textual representation of the user speech input is generated. The textual representation is parsed to determine a primary domain representing a user intent for the textual representation. A first substring from the textual representation that corresponds to a first attribute of the primary domain is identified. The identified first substring is parsed to determine a secondary domain representing a user intent for the first substring. A task flow comprising one or more tasks is performed based on the primary domain and the secondary domain.

Abstract: Systems and processes for operating a virtual assistant programmed to refer to shared domain concepts using concept nodes are provided. In an example process, user speech input is received. A textual representation of the user speech input is generated. The textual representation is parsed to determine a primary domain representing a user intent for the textual representation. A first substring from the textual representation that corresponds to a first attribute of the primary domain is identified. The identified first substring is parsed to determine a secondary domain representing a user intent for the first substring. A task flow comprising one or more tasks is performed based on the primary domain and the secondary domain.

Abstract: Systems and processes for identifying relevant domains for user inputs that include one or more ambiguous words are disclosed. The ambiguous words include words that may or may not refer to a named entity, such as a song, movie, book, etc. In one example, a textual representation of user speech can be received and processed to identify a candidate named entity. The possible parts of speech of the candidate named entity can be determined and compared to a predetermined set of parts of speech. In response to determining that the possible parts of speech of the candidate named entity do not include one or more of the predetermined set of parts of speech, a saliency score associated with the candidate named entity can be lowered. A domain for processing the textual representation of user speech can then be identified using the saliency score associated with the candidate named entity.

Abstract: Systems and processes for operating a virtual assistant programmed to refer to shared domain concepts using concept nodes are provided. In an example process, user speech input is received. A textual representation of the user speech input is generated. The textual representation is parsed to determine a primary domain representing a user intent for the textual representation. A first substring from the textual representation that corresponds to a first attribute of the primary domain is identified. The identified first substring is parsed to determine a secondary domain representing a user intent for the first substring. A task flow comprising one or more tasks is performed based on the primary domain and the secondary domain.

Abstract: Systems and processes for operating a virtual assistant programmed to refer to shared domain concepts using concept nodes are provided. In some examples, to process a textual representation of user speech using an active ontology having these concept nodes, a primary user intent can be determined from the textual representation of user speech. Concepts referred to by the primary user intent can be identified, and substrings of the textual representation of user speech corresponding to the concepts can be identified. Secondary user intents for the substrings can be determined and a task flow based on the primary user intent and the secondary user intents can be generated and performed.

Abstract: Systems and processes for identifying relevant domains for user inputs that include one or more ambiguous words are disclosed. The ambiguous words include words that may or may not refer to a named entity, such as a song, movie, book, etc. In one example, a textual representation of user speech can be received and processed to identify a candidate named entity. The possible parts of speech of the candidate named entity can be determined and compared to a predetermined set of parts of speech. In response to determining that the possible parts of speech of the candidate named entity do not include one or more of the predetermined set of parts of speech, a saliency score associated with the candidate named entity can be lowered. A domain for processing the textual representation of user speech can then be identified using the saliency score associated with the candidate named entity.

Abstract: Systems and processes for operating a virtual assistant programmed to refer to shared domain concepts using concept nodes are provided. In some examples, to process a textual representation of user speech using an active ontology having these concept nodes, a primary user intent can be determined from the textual representation of user speech. Concepts referred to by the primary user intent can be identified, and substrings of the textual representation of user speech corresponding to the concepts can be identified. Secondary user intents for the substrings can be determined and a task flow based on the primary user intent and the secondary user intents can be generated and performed.

Abstract: Natural language interface to a back-end application, incorporating synonyms, suggestions, and proposals. Roughly described, synonyms are automatically added to user input to enhance the natural language interpretation, whereas suggestions and proposals are offered to the user in an interaction, usually after an interpretation of prior user input. Suggestions and synonyms can be learned from user input, whereas proposals are programmed by a third party. The selection of synonyms, suggestions, and proposals for use with particular user input can be user input context-based so that further user input can maintain context by explicitly indicating that the same context is intended, and rewards-based reinforcement can be used to better focus suggestions and proposals on the characteristics of the particular user.

Abstract: Roughly described, a context reactive user interface which offers user-selectable on-screen choices or hints to help the user follow up in the context of his or her previous interactions. Alternatively or additionally, the system can offer on-screen choices which, when selected by the user, can invoke one or more back-end applications with entry fields pre-filled from the user's previous interactions or from other contextual information.

Abstract: Roughly described, a context reactive user interface which offers user-selectable on-screen choices or hints to help the user follow up in the context of his or her previous interactions. Alternatively or additionally, the system can offer on-screen choices which, when selected by the user, can invoke one or more back-end applications with entry fields pre-filled from the user's previous interactions or from other contextual information.

Abstract: Natural language interface to a back-end application, incorporating synonyms, suggestions, and proposals. Roughly described, synonyms are automatically added to user input to enhance the natural language interpretation, whereas suggestions and proposals are offered to the user in an interaction, usually after an interpretation of prior user input. Suggestions and synonyms can be learned from user input, whereas proposals are programmed by a third party. The selection of synonyms, suggestions, and proposals for use with particular user input can be context-based, and rewards-based reinforcement can be used to better focus suggestions and proposals on the characteristics of the particular user.

Abstract: Roughly described, a natural language interface to a back-end application incorporates synonyms automatically added to user input to enhance the natural language interpretation. Synonyms can be learned from user input and written into a synonyms database. Their selection can be based on tokens identified in user input. Natural language interpretation can be performed by agents arranged in a network, which parse the user input in a distributed manner. In an embodiment, a particular agent of the natural language interpreter receives a first message that includes the user input, returns a message claiming at least a portion of the user input, and subsequently receives a second message delegating actuation of at least that portion to the particular agent.