公开(公告)号：US11886976B1

公开(公告)日：2024-01-30

申请号：US18222395

申请日：2023-07-14

Applicant: Google LLC

Inventor： Tal Schuster ,  Adam Joshua Fisch ,  Jai Prakash Gupta ,  Mostafa Dehghani ,  Dara Bahri ,  Vinh Quoc Tran ,  Yi Tay ,  Donald Arthur Metzler, Jr.

IPC: G06N3/0455

CPC classification number: G06N3/0455

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating output sequences using auto-regressive decoder neural networks. In particular, during generation, adaptive early exiting is used to reduce the time required to generate the output sequence.

公开(公告)号：US20240289552A1

公开(公告)日：2024-08-29

申请号：US18564859

申请日：2022-05-27

Applicant: Google LLC

Inventor： Yi Tay ,  Dara Bahri ,  Donald Arthur Metzler, Jr. ,  Hyung Won Chung ,  Jai Prakash Gupta ,  Sebastian Nikolas Ruder ,  Simon Baumgartner ,  Vinh Quoc Tran ,  Zhen Qin

IPC: G06F40/284

CPC classification number: G06F40/284

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing a machine learning task on an input sequence of characters that has a respective character at each of a plurality of character positions to generate a network output. One of the systems includes a neural network configured to perform the machine learning task, the neural network comprising a gradient-based sub-word tokenizer and an output neural network. The gradient-based sub-word tokenizer is configured to apply a learned, i.e., flexible, sub-word tokenization strategy to the input sequence of characters to generate a sequence of latent sub-word representations. The output neural network is configured to process the latent sub-word representation to generate the network output for the task.

公开(公告)号：US20240169184A1

公开(公告)日：2024-05-23

申请号：US18426212

申请日：2024-01-29

Applicant: Google LLC

Inventor： Tal Schuster ,  Adam Joshua Fisch ,  Jai Prakash Gupta ,  Mostafa Dehghani ,  Dara Bahri ,  Vinh Quoc Tran ,  Yi Tay ,  Donald Arthur Metzler, JR.

IPC: G06N3/0455

CPC classification number: G06N3/0455

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating output sequences using auto-regressive decoder neural networks. In particular, during generation, adaptive early exiting is used to reduce the time required to generate the output sequence.

公开(公告)号：US20240020516A1

公开(公告)日：2024-01-18

申请号：US18222395

申请日：2023-07-14

Applicant: Google LLC

Inventor： Tal Schuster ,  Adam Joshua Fisch ,  Jai Prakash Gupta ,  Mostafa Dehghani ,  Dara Bahri ,  Vinh Quoc Tran ,  Yi Tay ,  Donald Arthur Metzler, Jr.

IPC: G06N3/0455

CPC classification number: G06N3/0455

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating output sequences using auto-regressive decoder neural networks. In particular, during generation, adaptive early exiting is used to reduce the time required to generate the output sequence.

公开(公告)号：US10967248B2

公开(公告)日：2021-04-06

申请号：US16439206

申请日：2019-06-12

Applicant: Google LLC

Inventor： Adam Lelkes ,  Colin Keogh ,  Regis McHugh Gaughan, III ,  Katrina Tempero ,  Cong Yu ,  Vinh Quoc Tran ,  Ziad Raymond Sultan

IPC: A63F9/24 ,  A63F3/04

Abstract: Methods and systems that facilitate generating and presenting a crossword puzzle. Methods include obtaining, from a content source, a plurality of data items. Using the plurality of data items, a dictionary of clue-word pairs are generated. A crossword layout is generated using a random crossword layout generator. The generated crossword layout is input to a model that outputs a likelihood that the input crossword layout results in a valid crossword. If the likelihood that the crossword layout results in a valid crossword puzzle satisfies a first threshold, a plurality of words in a set of clue-word pairs from among the plurality of clue-word pairs is inserted into the crossword layout. If the plurality of words inserted into the crossword layout results in a valid crossword puzzle, the crossword puzzle is provided to a user on a user device using the set of clue-word pairs.