公开(公告)号：US12265792B2

公开(公告)日：2025-04-01

申请号：US17526824

申请日：2021-11-15

Applicant: ADOBE INC.

Inventor： Rachit Bansal ,  Milan Aggarwal ,  Sumit Bhatia ,  Jivat Neet Kaur ,  Balaji Krishnamurthy

IPC: G06F40/295 ,  G06F16/332 ,  G06F16/3329 ,  G06N20/00

Abstract: Methods and systems are provided for facilitating generation and utilization of a commonsense contextualizing machine learning (ML) model, in accordance with embodiments described herein. In embodiments, a commonsense contextual ML model is trained by fine-tuning a pre-trained language model using a set of training path-sentence pairs. Each training path-sentence pair includes a commonsense path, identified via a commonsense knowledge graph, and a natural language sentence identified as contextually related to the commonsense path. The trained commonsense contextualizing ML model can then be used to generate a commonsense inference path for a text input. Such a commonsense inference path can include a sequence of entities and relations that provide commonsense context to the text input. Thereafter, the commonsense inference path can be provided to a natural language processing system for use in performing a natural language processing task.

公开(公告)号：US11997056B2

公开(公告)日：2024-05-28

申请号：US17897419

申请日：2022-08-29

Applicant: ADOBE INC.

Inventor： Sumit Bhatia ,  Jivat Neet Kaur ,  Rachit Bansal ,  Milan Aggarwal ,  Balaji Krishnamurthy

IPC: H04L51/02 ,  G06F40/295 ,  G06N5/022

CPC classification number: H04L51/02 ,  G06F40/295 ,  G06N5/022

Abstract: The technology described herein receives a natural-language sequence of words comprising multiple entities. The technology then identifies a plurality of entities in the natural-language sequence. The technology generates a masked natural-language sequence by masking a first entity in the natural-language sequence. The technology retrieves, from a knowledge base, information related to a second entity in the plurality of entities. The technology then trains a natural-language model to respond to a query. The training uses a first representation of the masked natural-language sequence, a second representation of the information, and the first entity.

公开(公告)号：US20230153534A1

公开(公告)日：2023-05-18

申请号：US17526824

申请日：2021-11-15

Applicant: ADOBE INC.

Inventor： Rachit Bansal ,  Milan Aggarwal ,  Sumit Bhatia ,  Jivat Neet Kaur ,  Balaji Krishnamurthy

IPC: G06F40/295 ,  G06F16/332 ,  G06N20/00

CPC classification number: G06F40/295 ,  G06F16/3329 ,  G06N20/00

Abstract: Methods and systems are provided for facilitating generation and utilization of a commonsense contextualizing machine learning (ML) model, in accordance with embodiments described herein. In embodiments, a commonsense contextual ML model is trained by fine-tuning a pre-trained language model using a set of training path-sentence pairs. Each training path-sentence pair includes a commonsense path, identified via a commonsense knowledge graph, and a natural language sentence identified as contextually related to the commonsense path. The trained commonsense contextualizing ML model can then be used to generate a commonsense inference path for a text input. Such a commonsense inference path can include a sequence of entities and relations that provide commonsense context to the text input. Thereafter, the commonsense inference path can be provided to a natural language processing system for use in performing a natural language processing task.