公开(公告)号：US20210357599A1

公开(公告)日：2021-11-18

申请号：US16922951

申请日：2020-07-07

Applicant: Google LLC

Inventor： Shruti Gupta ,  Jayakumar Hoskere

IPC: G06F40/58 ,  G06F40/253 ,  G06F40/30 ,  G06F40/166 ,  G06F40/211

Abstract: A system and method are disclosure for obtaining a set of candidate edits for a word of a sentence, wherein each of the set of candidate edits includes an edit word, identifying, in the sentence, a two or more surrounding words that each have a dependency relationship with the edit word, wherein at least one of the two or more surrounding words is identified irrespective of their proximity to the edit word, providing, as input to a grammar accuracy prediction model, the dependency relationship between the edit word and each of the surrounding words and the set of candidate edits, obtaining one or more outputs from the grammar accuracy prediction model, wherein the one or more outputs indicate grammatical accuracy of each candidate edit from the set in the sentence in view of the dependency relationship with surrounding words, and selecting the candidate edit with highest accuracy from the candidate edit set for the sentence.

公开(公告)号：US11636274B2

公开(公告)日：2023-04-25

申请号：US16922951

申请日：2020-07-07

Applicant: Google LLC

Inventor： Shruti Gupta ,  Jayakumar Hoskere

IPC: G06F40/58 ,  G06F40/253 ,  G06F40/211 ,  G06F40/166 ,  G06F40/30

Abstract: A set of candidate edits for a word of a sentence is obtained. Each of the set of candidate edits includes an edit word. Two or more surrounding words that each have a dependency relationship with the edit word are identified in the sentence. At least one of the two or more surrounding words is identified irrespective of their proximity to the edit word. The dependency relationship between the edit word and each of the surrounding words and the set of candidate edits is provided as input to a grammar accuracy prediction model. One or more outputs of the grammar accuracy prediction model are obtained. The one or more outputs indicate grammatical accuracy of each candidate edit from the set in the sentence in view of the dependency relationship with surrounding words. The candidate edit with highest accuracy is selected from the candidate edit set for the sentence.

公开(公告)号：US20240330580A1

公开(公告)日：2024-10-03

申请号：US18621892

申请日：2024-03-29

Applicant: Google LLC

Inventor： Behnoosh Hariri ,  Gregory George Galante ,  Rebecca Wenshu Hsieh ,  Princeton Tirin Poe ,  Gonzalo Fiorina ,  Barak Ben Noon ,  Miles Henrichs ,  Ahsan Wahab ,  Amer Mograbi ,  Christopher Gregory Tong ,  Nicholas Joseph Pesce ,  Andrew James Motika ,  John Gabriel D'Angelo ,  Tomer Aberbach ,  Grace Sytin Shih ,  Albert Orriols Puig ,  Jayakumar Hoskere

IPC: G06F40/186 ,  G06F40/103 ,  G06F40/20

CPC classification number: G06F40/186 ,  G06F40/103 ,  G06F40/20

Abstract: Systems and methods for generating personalized and structured content using a collaborative generator provide a user interface to a user computing system and receive a prompt from the user computing system via the user interface. The systems and methods provide the prompt to a generative model, with the generative model being a machine-learned model trained to process language input prompts to generate a language output. The systems and methods receive a generative output generated by the generative model in response to the prompt. Additionally, the systems and methods generate a modified output by modifying the generative output based at least in part on historical user data for a user associated with the prompt, and then provide the modified output via the user interface.

公开(公告)号：US20230259720A1

公开(公告)日：2023-08-17

申请号：US18306174

申请日：2023-04-24

Applicant: Google LLC

Inventor： Shruti Gupta ,  Jayakumar Hoskere

IPC: G06F40/58 ,  G06F40/253 ,  G06F40/211 ,  G06F40/166 ,  G06F40/30

CPC classification number: G06F40/58 ,  G06F40/253 ,  G06F40/211 ,  G06F40/166 ,  G06F40/30

Abstract: A semantic dependency relationship and/or a syntactic dependency relationship is determined between at least one word of a sentence and any of a set of surrounding words in the sentence. The determined semantic dependency relationship and/or the determined syntactic dependency relationship are provided as input to a machine learning model. One or more outputs of the machine learning model are obtained, the one or more outputs indicating, for a set of candidate edits for the at least one word of the sentence, a grammatical accuracy of each candidate edit of the set of candidate edits in view of the syntactic dependency relationship and/or the syntactic dependency relationship. A candidate edit is selected from the set of candidate edits based on the indicated grammatical accuracy of each candidate edit from the set of candidate edits.