公开(公告)号：US20230317066A1

公开(公告)日：2023-10-05

申请号：US17690609

申请日：2022-03-09

Applicant: Amazon Technologies, Inc.

Inventor： Jonathan Jakob Hueser ,  Fabian Triefenbach ,  Chandana Satya Prakash ,  Jin Cao ,  Wael Hamza ,  Mariusz Momotko

IPC: G10L15/18 ,  G10L15/22 ,  G10L15/06 ,  G06F40/295 ,  G06F40/30

CPC classification number: G10L15/1815 ,  G06F40/295 ,  G06F40/30 ,  G10L15/063 ,  G10L15/22 ,  G10L15/30

Abstract: Techniques for using a shared encoder and multiple different decoders for natural language understanding (NLU) tasks are described. The individual decoders are configured to perform different tasks using the output from one shared encoder. The decoders can process with respect to different domains and different languages. Using the shared encoder can reduce computation time during runtime. Using the shared encoder can reduce training costs (e.g., time and resources) when the system is updated to incorporate additional intents and entities. The system employs an attention mechanism to extract encoded representation data that can be used by the different decoders for its specific task.

公开(公告)号：US12266355B2

公开(公告)日：2025-04-01

申请号：US17690609

申请日：2022-03-09

Applicant: Amazon Technologies, Inc.

Inventor： Jonathan Jakob Hueser ,  Fabian Triefenbach ,  Chandana Satya Prakash ,  Jin Cao ,  Wael Hamza ,  Mariusz Momotko

IPC: G06F40/30 ,  G06F40/295 ,  G10L15/06 ,  G10L15/18 ,  G10L15/22 ,  G06F40/279 ,  G10L15/08 ,  G10L15/30

Abstract: Techniques for using a shared encoder and multiple different decoders for natural language understanding (NLU) tasks are described. The individual decoders are configured to perform different tasks using the output from one shared encoder. The decoders can process with respect to different domains and different languages. Using the shared encoder can reduce computation time during runtime. Using the shared encoder can reduce training costs (e.g., time and resources) when the system is updated to incorporate additional intents and entities. The system employs an attention mechanism to extract encoded representation data that can be used by the different decoders for its specific task.