Generating query variants using a trained generative model
AssigneeGoogle Inc.
InventorsJyrki Alakuijala, Christian Buck, Jannis Bulian, Massimiliano Ciaramita, Wojciech Gajewski, Andrea Gesmundo, Neil Houlsby, Wei Wang
Life of this patent
Estimating the term…
Abstract
Systems, methods, and computer readable media related to generating query variants for a submitted query. In many implementations, the query variants are generated utilizing a generative model. A generative model is productive, in that it can be utilized to actively generate a variant of a query based on application of tokens of the query to the generative model, and optionally based on application of additional input features to the generative model.
Claims20
A method implemented by one or more processors, the method comprising:
- receiving an original query, the original query generated based on user interface input of a user via a client device;
- applying, to a trained generative model:
- a location of the user,
- one or more attributes of the user that are determined based on one or more query submissions received prior to the receiving of the original query, and
- the original query;
- generating, based on application of the location of the user, application of the original query, and application of the one or more attributes of the user, to the trained generative model, generative output;
- subsequent to generating the generative output:
- generating, based on application of further input to the trained generative model, further generative output,
- wherein the further input is based on the generative output;
- generating an output based on the further generative output;
- and
- providing, in response to the original query, the output for presentation via the client device.
A system comprising:
- one or more storage devices storing instructions;
- and
- one or more processors operable to execute the instructions to:
- receive an original query, the original query generated based on user interface input of a user via a client device;
- apply, to a trained generative model:
- a location of the user,
- one or more attributes of the user that are determined based on one or more query submissions received prior to the receiving of the original query, and
- the original query;
- generate, based on application of the location of the user, application of the original query, and application of the one or more attributes of the user, to the trained generative model, generative output;
- subsequent to generating the generative output:
- generate, based on application of further input to the trained generative model, further generative output,
- wherein the further input is based on the generative output;
- generate an output based on the further generative output;
- and
- provide, in response to the original query, the output for presentation via the client device.
Dependencies are inferred from the claim text.