Assistive digital form authoring

A system comprising:

• a processing device;
• and
• a memory component storing instructions, which when executed by the processing device, cause the processing device to perform operations comprising:
• receiving form data describing a plurality of different digital forms;
• identifying, based on the form data, a plurality of candidate search outputs for a plurality of search inputs;
• generating a group of candidate embedding vectors in a latent space corresponding to the plurality of candidate search outputs, the generating performed using a machine learning model;
• receiving input data describing a subsequent search input associated with a digital form;
• generating an input embedding vector that represents the subsequent search input in the latent space using the machine learning model;
• identifying a candidate embedding vector included in the group of candidate embedding vectors based on a distance between the input embedding vector and the identified candidate embedding vector in the latent space;
• and
• generating an indication of a search output associated with the digital form for display in a user interface based on the identified candidate embedding vector.

A non-transitory computer-readable storage medium storing executable instructions, which when executed by a processing device, cause the processing device to perform operations comprising:

• receiving form data describing a plurality of different digital forms;
• identifying, based on the form data, a plurality of candidate search outputs for a plurality of search inputs;
• generating a group of candidate embedding vectors in a latent space corresponding to the plurality of candidate search outputs, the generating performed using a machine learning model;
• receiving input data describing an interaction relative to a digital form displayed in a user interface of an application for editing digital forms;
• generating an input embedding vector that represents the interaction in the latent space using the machine learning model;
• identifying a candidate embedding vector included in the group of candidate embedding vectors based on a distance between the input embedding vector and the identified candidate embedding vector in the latent space;
• and
• generating an indication of a form element for display in the user interface based on the identified candidate embedding vector.