公开(公告)号：US20230385321A1

公开(公告)日：2023-11-30

申请号：US18227450

申请日：2023-07-28

Applicant: Google LLC

Inventor： Nikunj Agrawal ,  Mukund Sundararajan ,  Shrikant Ravindra Shanbhag ,  Kedar Dhamdhere ,  Garima ,  Kevin Snow Mccurley ,  Rohit Ananthakrishna ,  Daniel Adam Gundrum ,  Juyun June Song ,  Rifat Ralfi Nahmias

IPC: G06F16/338 ,  G06F3/16 ,  G06T11/20 ,  G06F16/332 ,  G06F16/33 ,  G06F40/18 ,  G06F40/58

CPC classification number: G06F16/338 ,  G06F3/167 ,  G06T11/206 ,  G06F16/3326 ,  G06F16/3337 ,  G06F40/18 ,  G06F40/58 ,  G06F40/205

Abstract: Systems and methods are disclosed herein for processing a natural language query on data tables. According to some embodiments, a query term is obtained from a natural language query. A table summary is prepared based on the query term and a formula of the natural language query is generated based on the table summary. A result is generated based on the formula. Responsive to receiving negative feedback to the result, one or more of the table summary or the formula is disassociated from the query term.

公开(公告)号：US11288800B1

公开(公告)日：2022-03-29

申请号：US16549898

申请日：2019-08-23

Applicant: Google LLC

Inventor： Amir Najmi ,  Ankur Taly ,  Mukund Sundararajan ,  Rory Abbott Sayres ,  Jinhau Xu

IPC: G06T7/00 ,  G06N3/08 ,  G06T5/00 ,  G06F3/14 ,  G06T11/00

Abstract: Introduced here are diagnostic platforms able to attribute an output produced by a neural network to its input, as well as communicate the relationship between the output and input in a comprehensible manner. Neural networks are increasingly being used for critical tasks, such as detecting the presence/progression of medical conditions. Accordingly, the importance of explaining how these neural networks produce outputs has grown in importance. By explaining how outputs are produced by a neural network, a diagnostic platform can build trust with medical professionals responsible for interpreting the outputs, identify possible modes of neural network failure, and identify the latent variable(s) responsible for producing a given output.

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：US20210271697A1

公开(公告)日：2021-09-02

申请号：US17306666

申请日：2021-05-03

Applicant: Google LLC

Inventor： Nikunj Agrawal ,  Mukund Sundararajan ,  Shrikant Ravindra Shanbhag ,  Kedar Dhamdhere ,  Null Garima ,  Kevin Snow Mccurley ,  Rohit Ananthakrishna ,  Daniel Adam Gundrum ,  Juyun June Song ,  Rifat Ralfi Nahmias

IPC: G06F16/338 ,  G06F3/16 ,  G06T11/20 ,  G06F16/332 ,  G06F16/33 ,  G06F40/18 ,  G06F40/58

Abstract: Systems and methods are disclosed herein for processing a natural language query on data tables. According to some embodiments, a natural language query may be originated by a user via a user interface. The natural language query may be parsed to obtain a query term, and a grid range may be identified in a data table as relevant to the query term. A table summary may be prepared including a plurality of characteristics based on the grid range. A logic operation may then be determined to apply on the plurality of characteristics to derive the query term. The logic operation may then be translated into a formula executable on the data table, and the formula is applied on the data table to generate a result in response to the natural language query.

公开(公告)号：US11714841B2

公开(公告)日：2023-08-01

申请号：US17306666

申请日：2021-05-03

Applicant: Google LLC

Inventor： Nikunj Agrawal ,  Mukund Sundararajan ,  Shrikant Ravindra Shanbhag ,  Kedar Dhamdhere ,  Null Garima ,  Kevin Snow Mccurley ,  Rohit Ananthakrishna ,  Daniel Adam Gundrum ,  Juyun June Song ,  Rifat Ralfi Nahmias

IPC: G06F16/00 ,  G06F16/338 ,  G06F3/16 ,  G06T11/20 ,  G06F16/332 ,  G06F16/33 ,  G06F40/18 ,  G06F40/58 ,  G06F40/205

CPC classification number: G06F16/338 ,  G06F3/167 ,  G06F16/3326 ,  G06F16/3337 ,  G06F40/18 ,  G06F40/58 ,  G06T11/206 ,  G06F40/205

Abstract: Systems and methods are disclosed herein for processing a natural language query on data tables. According to some embodiments, a natural language query may be originated by a user via a user interface. The natural language query may be parsed to obtain a query term, and a grid range may be identified in a data table as relevant to the query term. A table summary may be prepared including a plurality of characteristics based on the grid range. A logic operation may then be determined to apply on the plurality of characteristics to derive the query term. The logic operation may then be translated into a formula executable on the data table, and the formula is applied on the data table to generate a result in response to the natural language query.