公开(公告)号：US20230143721A1

公开(公告)日：2023-05-11

申请号：US17524282

申请日：2021-11-11

Applicant: ADOBE INC.

Inventor： Sungchul Kim ,  Subrata Mitra ,  Ruiyi Zhang ,  Rui Wang ,  Handong Zhao ,  Tong Yu

IPC: G06F40/295 ,  G06N20/00

CPC classification number: G06F40/295 ,  G06N20/00

Abstract: Embodiments of the technology described herein describe a machine classifier capable of continually learning new classes through a continual few-shot learning approach. A natural language processing (NLP) machine classifier may initially be trained to identify a plurality of other classes through a conventional training process. In order to learn a new class, natural-language training data for a new class is generated. The training data for the new class may be few-shot training data. The training also uses synthetic training data that represents each of the plurality of other classes. The synthetic training data may be generated through a model inversion of the original classifier. The synthetic training data and the natural-language training data are used to retrain the NLP classifier to identify text in the plurality of other classes and the new class using.

公开(公告)号：US20240273296A1

公开(公告)日：2024-08-15

申请号：US18625884

申请日：2024-04-03

Applicant: Adobe Inc.

Inventor： Sungchul KIM ,  Subrata MITRA ,  Ruiyi Zhang ,  Rui Wang ,  Handong ZHAO ,  Tong YU

IPC: G06F40/295 ,  G06N20/00

CPC classification number: G06F40/295 ,  G06N20/00

Abstract: Embodiments of the technology described herein describe a machine classifier capable of continually learning new classes through a continual few-shot learning approach. A natural language processing (NLP) machine classifier may initially be trained to identify a plurality of other classes through a conventional training process. In order to learn a new class, natural-language training data for a new class is generated. The training data for the new class may be few-shot training data. The training also uses synthetic training data that represents each of the plurality of other classes. The synthetic training data may be generated through a model inversion of the original classifier. The synthetic training data and the natural-language training data are used to retrain the NLP classifier to identify text in the plurality of other classes and the new class using.

公开(公告)号：US11995403B2

公开(公告)日：2024-05-28

申请号：US17524282

申请日：2021-11-11

Applicant: ADOBE INC.

Inventor： Sungchul Kim ,  Subrata Mitra ,  Ruiyi Zhang ,  Rui Wang ,  Handong Zhao ,  Tong Yu

IPC: G06F40/295 ,  G06N20/00

CPC classification number: G06F40/295 ,  G06N20/00

Abstract: Embodiments of the technology described herein describe a machine classifier capable of continually learning new classes through a continual few-shot learning approach. A natural language processing (NLP) machine classifier may initially be trained to identify a plurality of other classes through a conventional training process. In order to learn a new class, natural-language training data for a new class is generated. The training data for the new class may be few-shot training data. The training also uses synthetic training data that represents each of the plurality of other classes. The synthetic training data may be generated through a model inversion of the original classifier. The synthetic training data and the natural-language training data are used to retrain the NLP classifier to identify text in the plurality of other classes and the new class using.