Abstract: A device configured to perform data analytics comprising a memory and a processor may be configured to perform the techniques described in this disclosure. The memory may store multi-dimensional data. The processor may receive a sequence of inputs defining a recipe for analyzing the multi-dimensional data according to a language sub-surface specifying a natural language containment hierarchy defining a grammar for a natural language as a hierarchical arrangement of a plurality of language sub-surfaces. The processor may also receive data indicative of a summarized narration of the recipe and parameterize a field of the summarized narration to insert a user adjustable parameter that enables manipulation of the underlying recipe and obtain a parameterized summary that includes the user adjustable parameter. The processor may next present, via a first user interface, the parameterized summary.

Abstract: In general, techniques are described for various aspects of accessing datasets. A device comprising a memory configured to store the dataset, and a processor may be configured to perform the techniques. The processor may expose a language sub-surface specifying a natural language containment hierarchy defining a grammar for a natural language as a hierarchical arrangement of a plurality of language sub-surfaces. The processor may receive a query to access the dataset, the query conforming to a portion of the natural language provided by the exposed language sub-surface. The processor may transform the query into one or more statements that conform to a formal syntax associated with the dataset, access, based on the one or more statements, the dataset to obtain a query result, and output the query result.

Abstract: A device comprising a processor and a memory may be configured to perform various aspects of the techniques described in this disclosure. The processor may present, via a first portion of a user interface, an interactive text box in which a user may enter the data indicative of the current input, present, via a second portion of the user interface, an interactive log of previous inputs entered prior the current input, and present, via a third portion of the user interface, a graphical representation of result data obtained responsive to the data indicative of the current input. The second portion of the user interface and the third portion of the user interface may be separately scrollable but coupled such that interactions in either the second portion of the user interface or the third portion of the user interface synchronize the second portion of the user interface and the third portion of the user interface. The memory may store the data indicative of the current input.

Abstract: In general, techniques are described by which to provide constrained natural language processing. A device comprising a processor and a memory may be configured to perform the techniques. The processor may expose a language sub-surface specifying a natural language containment hierarchy defining a grammar for a natural language as a hierarchical arrangement of language sub-surfaces. The processor may also receive the data indicative of the input that conforms with the portion of the language provided by the exposed language sub-surface, and process the data indicative of the input to identify an intent of the user from a plurality of intents associated with the portion of the language. The processor may next execute a process associated with the identified intent to perform an operation. The memory may store the data indicative of the input.