Provided is a system and method for detecting a SQL command from a natural language input using neural networks which works even when the SQL command has not been seen before by the neural networks. In one example, the method may include storing a candidate set comprising structured query language (SQL) templates paired with respective text values, reducing, via a first predictive network, the candidate set into a subset of candidates based on a natural language input and the text values included in the candidate set, selecting, via a second predictive network, an SQL template from among the subset of candidates based on the natural language input and text values included in the subset of candidates, and determining a SQL command that corresponds to the natural language input based on the selected SQL template and content from the natural language input.

At a first chatbot, a query expressed in natural language form is received. It is determined that responding to the query requires data external to the first chatbot. From a data source external to the first chatbot, response data corresponding to the query is obtained. Using the response data, the query is responded to in natural language form. Using the response data, the first chatbot is updated.

Generally, the present disclosure is directed to systems and methods for performing task-oriented response generation that can provide advantages for artificial intelligence systems or other computing systems that include natural language processing for interpreting user input. Example implementations can process natural language descriptions of various services that can be accessed by the system. In response to a natural language input, systems can identify relevant values for executing one of the service(s), based in part on comparing embedded representations of the natural language input and the natural language description using a machine learned model.

In one embodiment, a method includes receiving an initial input in a first modality from a first user from a client system associated with the first user, determining one or more intents corresponding to the initial input by an intent-understanding module, generating one or more candidate continuation-inputs based on the one or more intents, where the one or more candidate continuation-inputs are in one or more candidate modalities, respectively, and wherein the candidate modalities are different from the first modality, and sending instructions for presenting one or more suggested inputs corresponding to one or more of the candidate continuation-inputs to the client system.

Methods, systems and computer readable media are provided for automatically creating a semantic model of a relational database for processing natural language queries. A computing device automatically extracts relational database metadata. The computing device prompts a user to enter textual labels for columns of the extracted metadata. The computing device automatically generates a schema annotation file based upon the relational database metadata and the textual labels for the columns. A natural language query is processed for the relational database using the schema annotation file.

Examples of the present disclosure describe systems and methods for generating multiple semantic hypotheses for search query intent understanding. In aspects, a search query may be received by a query analysis component associated with a search system. The query analysis component may be used to evaluate the search query for ambiguity in the domain, intent, and/or slot(s) of the search query. A set of hypotheses representing for one or more combinations of the domain, intent, and/or slot(s) of the search query may be generated. The set of hypotheses may be scored and/or ranked. Based on the scores/ranks, one or more of the hypotheses in the set of hypotheses may be provided to a user and/or one or more processing components accessible to the search system.

A computer-implemented method of performing an incremental specification of a query includes extracting text from each of a plurality of participants in a dialog. A contextual information is determined of the extracted text of one or more of the plurality of participants. A dialog understanding operation is performed by processing at least the contextual information of the extracted text in a knowledge graph to identify in the dialog at least one or more of a structural gap, an information about entities, relationships, and actions. Query information is provided responsive to the dialog for at least one of filling the identified structural gap, or for providing additional information about one or more of the identified entities, relationships or actions in the dialog.

A method and system are described that provide responses to natural language queries regarding the performance of a business. The method and system provide for crowd-sourced data to determine natural language query suggestions to transmit to a user, based upon previously submitted questions of the user and/or similar merchants to the user. Natural language query suggestions may be provided as utterances to a keyboard of a merchant user. The merchant user may select one or more suggestions provided. The use of natural language queries and responses allows a merchant without a business intelligence background to obtain business insights easily and accurately assess his performance (e.g., against similar merchants, etc.) without personally identifiable or confidential information of other merchants being compromised.

Systems and methods are presented herein for recording portions of a media asset relevant to recording criteria. A media application receives input indicating the recording criteria and identifying a first keyword. The media application accesses a data structure to identify a first node associated with the first keyword. The data structure includes the first node and a plurality of nodes connected to the first node via a plurality of paths. The media application receiving audio component data for a portion of the media asset extracts a term from the audio component data, and identifies a second node in the data structure that is associated with the extracted term. The media application calculates a path score for the portion of the media asset based on a path size in the data structure between the first node and the second node. When the score is high enough, the portion of the media asset is recorded.

The present disclosure provides task delegation and cooperation for automated assistants. In one example, a method performed by a processing system that is in communication with a plurality of automated assistants includes receiving, a query indicating a task with which a user desires assistance, parsing the task into a plurality of sub-tasks including a first sub-task and a second sub-task, identifying a first automated assistant of the plurality of automated assistants that is capable of performing the first sub-task and a second automated assistant of the plurality of automated assistants that is capable of performing the second sub-task, and formulating a proposal for responding to the query, wherein the proposal comprises a sequence in which the plurality of sub-tasks is to be performed and a mapping that assigns the first sub-task to the first automated assistant and the second sub-task to the second automated assistant.