公开(公告)号：US20230297603A1

公开(公告)日：2023-09-21

申请号：US17655395

申请日：2022-03-18

Applicant: ADOBE INC.

Inventor： Meryem M'hamdi ,  Doo Soon Kim ,  Franck Dernoncourt ,  Trung Huu Bui

IPC: G06F16/33 ,  G06F40/35 ,  G06F40/279 ,  G06N20/00

CPC classification number: G06F16/3344 ,  G06F40/35 ,  G06F40/279 ,  G06N20/00

Abstract: Systems and methods for natural language processing are described. Embodiments of the present disclosure identify a task set including a plurality of pseudo tasks, wherein each of the plurality of pseudo tasks includes a support set corresponding to a first natural language processing (NLP) task and a query set corresponding to a second NLP task; update a machine learning model in an inner loop based on the support set; update the machine learning model in an outer loop based on the query set; and perform the second NLP task using the machine learning model.

公开(公告)号：US20250068924A1

公开(公告)日：2025-02-27

申请号：US18449291

申请日：2023-08-14

Applicant: Adobe Inc.

Inventor： Meryem M'hamdi ,  Seunghyun Yoon ,  Franck Dernoncourt ,  Trung Bui

IPC: G06N3/096 ,  G06F40/30 ,  G06F40/40

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for providing multilingual semantic search results utilizing meta-learning and knowledge distillation. For example, in some implementations, the disclosed systems perform a first inner learning loop for a monolingual to bilingual meta-learning task for a teacher model. Additionally, in some implementations, the disclosed systems perform a second inner learning loop for a bilingual to multilingual meta-learning task for a student model. In some embodiments, the disclosed systems perform knowledge distillation based on the first inner learning loop for the monolingual to bilingual meta-learning task and the second inner learning loop for the bilingual to multilingual meta-learning task. Moreover, in some embodiments, the disclosed systems perform an outer learning loop and update parameters of a deep learning language model based on the first inner learning loop, the second inner learning loop, and the knowledge distillation.