公开(公告)号：US20250094456A1

公开(公告)日：2025-03-20

申请号：US18887751

申请日：2024-09-17

Applicant: GOOGLE LLC

Inventor： Kelvin Gu ,  Zhuyun Dai ,  Panupong Pasupat ,  Chen Elkind ,  Eran Ofek ,  Hagai Taitelbaum ,  Mukund Sundararajan ,  Vered Cohen ,  Itay Karo ,  Norbert Kalb ,  Yossi Matias ,  Tej Toor ,  Teghan Tracy

IPC: G06F16/332 ,  G06F16/33 ,  G06F16/35

Abstract: Implementations are described herein for identifying potentially false information in generative model output by performing entailment evaluation of generative model output. In various implementations, data indicative of a query may be processed to generate generative model output. Textual fragments may be extracted from the generative model output, and a subset of the textual fragments may be classified as being suitable for textual entailment analysis. Textual entailment analysis may be performed on each textual fragment of the subset, including formulating a search query based on the textual fragment, retrieving document(s) responsive to the search query, and processing the textual fragment and the document(s) using entailment machine learning model(s) to generate prediction(s) of whether the at least one document corroborates or contradicts the textual fragment. When natural language (NL) responsive to the query is rendered at a client device, annotation(s) may be rendered to express the prediction(s).

公开(公告)号：US20200372356A1

公开(公告)日：2020-11-26

申请号：US16883772

申请日：2020-05-26

Applicant: Google LLC

Inventor： William Chan ,  Mitchell Thomas Stern ,  Nikita Kitaev ,  Kelvin Gu ,  Jakob D. Uszkoreit

IPC: G06N3/08 ,  G06N3/04 ,  G06F40/237

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing sequence modeling tasks using insertions. One of the methods includes receiving a system input that includes one or more source elements from a source sequence and zero or more target elements from a target sequence, wherein each source element is selected from a vocabulary of source elements and wherein each target element is selected from a vocabulary of target elements; generating a partial concatenated sequence that includes the one or more source elements from the source sequence and the zero or more target elements from the target sequence, wherein the source and target elements arranged in the partial concatenated sequence according to a combined order; and generating a final concatenated sequence that includes a finalized source sequence and a finalized target sequence, wherein the finalized target sequence includes one or more target elements.

公开(公告)号：US20240028893A1

公开(公告)日：2024-01-25

申请号：US18321696

申请日：2023-05-22

Applicant: Google LLC

Inventor： William Chan ,  Mitchell Thomas Stern ,  Nikita Kitaev ,  Kelvin Gu ,  Jakob D. Uszkoreit

IPC: G06N3/08 ,  G06F40/237 ,  G06N3/04 ,  G06N3/084

CPC classification number: G06N3/08 ,  G06F40/237 ,  G06N3/04 ,  G06N3/084

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing sequence modeling tasks using insertions. One of the methods includes receiving a system input that includes one or more source elements from a source sequence and zero or more target elements from a target sequence, wherein each source element is selected from a vocabulary of source elements and wherein each target element is selected from a vocabulary of target elements; generating a partial concatenated sequence that includes the one or more source elements from the source sequence and the zero or more target elements from the target sequence, wherein the source and target elements arranged in the partial concatenated sequence according to a combined order; and generating a final concatenated sequence that includes a finalized source sequence and a finalized target sequence, wherein the finalized target sequence includes one or more target elements.

公开(公告)号：US11003865B1

公开(公告)日：2021-05-11

申请号：US16879457

申请日：2020-05-20

Applicant: Google LLC

Inventor： Kenton Chiu Tsun Lee ,  Kelvin Gu ,  Zora Tung ,  Panupong Pasupat ,  Ming-Wei Chang

IPC: G06F40/49 ,  G06F40/56 ,  G06N5/02 ,  G06K9/62

Abstract: Systems and methods for pre-training and fine-tuning of neural-network-based language models are disclosed in which a neural-network-based textual knowledge retriever is trained along with the language model. In some examples, the knowledge retriever obtains documents from an unlabeled pre-training corpus, generates its own training tasks, and learns to retrieve documents relevant to those tasks. In some examples, the knowledge retriever is further refined using supervised open-QA questions. The framework of the present technology provides models that can intelligently retrieve helpful information from a large unlabeled corpus, rather than requiring all potentially relevant information to be stored implicitly in the parameters of the neural network. This framework may thus reduce the storage space and complexity of the neural network, and also enable the model to more effectively handle new tasks that may be different than those on which it was pre-trained.

公开(公告)号：US12086715B2

公开(公告)日：2024-09-10

申请号：US18321696

申请日：2023-05-22

Applicant: Google LLC

Inventor： William Chan ,  Mitchell Thomas Stern ,  Nikita Kitaev ,  Kelvin Gu ,  Jakob D. Uszkoreit

IPC: G06F40/30 ,  G06F40/237 ,  G06N3/04 ,  G06N3/08 ,  G06N3/084

CPC classification number: G06N3/08 ,  G06F40/237 ,  G06N3/04 ,  G06N3/084

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing sequence modeling tasks using insertions. One of the methods includes receiving a system input that includes one or more source elements from a source sequence and zero or more target elements from a target sequence, wherein each source element is selected from a vocabulary of source elements and wherein each target element is selected from a vocabulary of target elements; generating a partial concatenated sequence that includes the one or more source elements from the source sequence and the zero or more target elements from the target sequence, wherein the source and target elements arranged in the partial concatenated sequence according to a combined order; and generating a final concatenated sequence that includes a finalized source sequence and a finalized target sequence, wherein the finalized target sequence includes one or more target elements.

公开(公告)号：US20230205994A1

公开(公告)日：2023-06-29

申请号：US17561581

申请日：2021-12-23

Applicant: Google LLC

Inventor： Jason Weng Wei ,  Maarten Paul Bosma ,  Yuzhe Zhao, JR. ,  Kelvin Gu ,  Quoc V. Le

IPC: G06F40/284 ,  G06F40/30 ,  G06N3/10 ,  G06N5/04

CPC classification number: G06F40/284 ,  G06F40/30 ,  G06N3/10 ,  G06N5/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a machine learning task on an input to generate an output. In one aspect, one of the method includes receiving input data that describes an input of a machine learning task; receiving candidate output data that describes a set of candidate classification outputs of the machine learning task for the input; generating an input sequence that includes the input and the set of candidate classification outputs; processing the input sequence using a neural network to generate a network output that specifies a respective score for each candidate classification output in the set of candidate classification outputs; and generating an output of the machine learning task for the input, comprising selecting, as the output, a selected candidate classification output from the set of candidate classification outputs using the respective scores.

公开(公告)号：US11657277B2

公开(公告)日：2023-05-23

申请号：US16883772

申请日：2020-05-26

Applicant: Google LLC

Inventor： William Chan ,  Mitchell Thomas Stern ,  Nikita Kitaev ,  Kelvin Gu ,  Jakob D. Uszkoreit

IPC: G10L25/00 ,  G10L21/00 ,  G06F40/30 ,  G06N3/08 ,  G06F40/237 ,  G06N3/04 ,  G06N3/084

CPC classification number: G06N3/08 ,  G06F40/237 ,  G06N3/04 ,  G06N3/084

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing sequence modeling tasks using insertions. One of the methods includes receiving a system input that includes one or more source elements from a source sequence and zero or more target elements from a target sequence, wherein each source element is selected from a vocabulary of source elements and wherein each target element is selected from a vocabulary of target elements; generating a partial concatenated sequence that includes the one or more source elements from the source sequence and the zero or more target elements from the target sequence, wherein the source and target elements arranged in the partial concatenated sequence according to a combined order; and generating a final concatenated sequence that includes a finalized source sequence and a finalized target sequence, wherein the finalized target sequence includes one or more target elements.