公开(公告)号：US11113479B2

公开(公告)日：2021-09-07

申请号：US16569513

申请日：2019-09-12

Applicant: Adobe Inc.

Inventor： Quan Tran ,  Tuan Manh Lai ,  Trung Bui

IPC: G06F40/00 ,  G06F40/44 ,  G06N5/04 ,  G06K9/62 ,  G06F17/16 ,  G06F16/9032

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that can determine an answer to a query based on matching probabilities for combinations of respective candidate answers. For example, the disclosed systems can utilize a gated-self attention mechanism (GSAM) to interpret inputs that include contextual information, a query, and candidate answers. The disclosed systems can also utilize a memory network in tandem with the GSAM to form a gated self-attention memory network (GSAMN) to refine outputs or predictions over multiple reasoning hops. Further, the disclosed systems can utilize transfer learning of the GSAM/GSAMN from an initial training dataset to a target training dataset.

公开(公告)号：US20210081503A1

公开(公告)日：2021-03-18

申请号：US16569513

申请日：2019-09-12

Applicant: Adobe Inc.

Inventor： Quan Tran ,  Tuan Manh Lai ,  Trung Bui

IPC: G06F17/28 ,  G06N5/04 ,  G06F16/9032 ,  G06F17/16 ,  G06K9/62

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that can determine an answer to a query based on matching probabilities for combinations of respective candidate answers. For example, the disclosed systems can utilize a gated-self attention mechanism (GSAM) to interpret inputs that include contextual information, a query, and candidate answers. The disclosed systems can also utilize a memory network in tandem with the GSAM to form a gated self-attention memory network (GSAMN) to refine outputs or predictions over multiple reasoning hops. Further, the disclosed systems can utilize transfer learning of the GSAM/GSAMN from an initial training dataset to a target training dataset.