Search System Having Task-Based Machined-Learned Models

A computer-implemented method, the method comprising:

• receiving, by a computing system comprising one or more processors, a first user query from a user device;
• determining, using a multi-task machine-learned model, that the first user query is associated with a first subtask and a second subtask of a task;
• performing, using the multi-task machine-learned model, a first query search for the first subtask to obtain a first content item associated with the first subtask;
• performing, using the multi-task machine-learned model, a second query search for the second subtask to obtain a second content item associated with the second subtask;
• causing a presentation, on a display of the user device, of a search result page, the search result page displaying the first content item and the second content item;
• modifying a user interaction score associated with the second subtask in response to receiving a user interaction with the second content item;
• and
• updating, based on the user interaction score, the search result page to include a third content item as the search result page is being scrolled, the third content item being associated with the second subtask.

One or more non-transitory computer-readable media that collectively store instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform operations, the operations comprising:

• receiving a first user query from a user device;
• determining, using a multi-task machine-learned model, that the first user query is associated with a first subtask and a second subtask of a task;
• performing, using the multi-task machine-learned model, a first query search for the first subtask to obtain a first content item associated with the first subtask;
• performing, using the multi-task machine-learned model, a second query search for the second subtask to obtain a second content item associated with the second subtask;
• causing a presentation, on a display of the user device, of a search result page, the search result page displaying the first content item and the second content item;
• modifying a user interaction score associated with the second subtask in response to receiving a user interaction with the second content item;
• and
• updating, based on the user interaction score, the search result page to include a third content item as the search result page is being scrolled, the third content item being associated with the second subtask.