Techniques for transforming natural language conversation into a visualization representation

One or more non-transitory computer-readable media storing instructions which, when executed by one or more processors, cause a system to perform operations comprising:

• providing, to a machine learning model, an input comprising a natural language utterance and a schema representation, wherein the schema representation comprises one or more fact entities and a set of visualization entities, and wherein the set of visualization entities comprises at least one hub entity connected to the one or more fact entities via a link attribute;
• generating, by the machine learning model and based on the input, an intermediate logical form that represents a visualization action, wherein the intermediate logical form maps one or more words in the natural language utterance to the at least one hub entity;
• and
• generating, based on the intermediate logical form, a command for a computing system to execute the visualization action.

A system comprising:

• one or more processors;
• and
• one or more computer-readable media storing instructions which, when executed by the one or more processors, cause the system to perform operations comprising:
• providing, to a machine learning model, an input comprising a natural language utterance and a schema representation, wherein the schema representation comprises one or more fact entities and a set of visualization entities, and wherein the set of visualization entities comprises at least one hub entity connected to the one or more fact entities via a link attribute;
• generating, by the machine learning model and based on the input, an intermediate logical form that represents a visualization action, wherein the intermediate logical form maps one or more words in the natural language utterance to the at least one hub entity;
• and
• generating, based on the intermediate logical form, a command for a computing system to execute the visualization action.