公开(公告)号：US20240153499A1

公开(公告)日：2024-05-09

申请号：US18532969

申请日：2023-12-07

Applicant: Amazon Technologies, Inc.

Inventor： Angeliki Metallinou ,  Rahul Goel ,  Vishal Ishwar

IPC: G10L15/16 ,  G06F3/16 ,  G10L15/02 ,  G10L15/14 ,  G10L15/197 ,  G10L15/26

CPC classification number: G10L15/16 ,  G06F3/167 ,  G10L15/02 ,  G10L15/144 ,  G10L15/197 ,  G10L15/26 ,  G10L2015/025

Abstract: Multi-modal natural language processing systems are provided. Some systems are context-aware systems that use multi-modal data to improve the accuracy of natural language understanding as it is applied to spoken language input. Machine learning architectures are provided that jointly model spoken language input (“utterances”) and information displayed on a visual display (“on-screen information”). Such machine learning architectures can improve upon, and solve problems inherent in, existing spoken language understanding systems that operate in multi-modal contexts.

公开(公告)号：US11842727B2

公开(公告)日：2023-12-12

申请号：US17659612

申请日：2022-04-18

Applicant: Amazon Technologies, Inc.

Inventor： Angeliki Metallinou ,  Rahul Goel ,  Vishal Ishwar

IPC: G10L15/16 ,  G10L15/183 ,  G10L15/14 ,  G10L15/197 ,  G06F3/16 ,  G10L15/02 ,  G10L15/26

CPC classification number: G10L15/16 ,  G06F3/167 ,  G10L15/02 ,  G10L15/144 ,  G10L15/197 ,  G10L15/26 ,  G10L2015/025

Abstract: Multi-modal natural language processing systems are provided. Some systems are context-aware systems that use multi-modal data to improve the accuracy of natural language understanding as it is applied to spoken language input. Machine learning architectures are provided that jointly model spoken language input (“utterances”) and information displayed on a visual display (“on-screen information”). Such machine learning architectures can improve upon, and solve problems inherent in, existing spoken language understanding systems that operate in multi-modal contexts.

公开(公告)号：US20220246139A1

公开(公告)日：2022-08-04

申请号：US17659612

申请日：2022-04-18

Applicant: Amazon Technologies, Inc.

Inventor： Angeliki Metallinou ,  Rahul Goel ,  Vishal Ishwar

IPC: G10L15/16 ,  G10L15/14 ,  G10L15/197 ,  G06F3/16 ,  G10L15/02 ,  G10L15/26

Abstract: Multi-modal natural language processing systems are provided. Some systems are context-aware systems that use multi-modal data to improve the accuracy of natural language understanding as it is applied to spoken language input. Machine learning architectures are provided that jointly model spoken language input (“utterances”) and information displayed on a visual display (“on-screen information”). Such machine learning architectures can improve upon, and solve problems inherent in, existing spoken language understanding systems that operate in multi-modal contexts.

公开(公告)号：US20200251098A1

公开(公告)日：2020-08-06

申请号：US16723762

申请日：2019-12-20

Applicant: Amazon Technologies, Inc.

Inventor： Angeliki Metallinou ,  Rahul Goel ,  Vishal Ishwar

IPC: G10L15/16 ,  G10L15/02 ,  G10L15/26 ,  G06F3/16 ,  G10L15/197 ,  G10L15/14

Abstract: Multi-modal natural language processing systems are provided. Some systems are context-aware systems that use multi-modal data to improve the accuracy of natural language understanding as it is applied to spoken language input. Machine learning architectures are provided that jointly model spoken language input (“utterances”) and information displayed on a visual display (“on-screen information”). Such machine learning architectures can improve upon, and solve problems inherent in, existing spoken language understanding systems that operate in multi-modal contexts.

公开(公告)号：US10515625B1

公开(公告)日：2019-12-24

申请号：US15828174

申请日：2017-11-30

Applicant: Amazon Technologies, Inc.

Inventor： Angeliki Metallinou ,  Rahul Goel ,  Vishal Ishwar

IPC: G10L15/16 ,  G10L15/14 ,  G10L15/197 ,  G06F3/16 ,  G10L15/26 ,  G10L15/02

Abstract: Multi-modal natural language processing systems are provided. Some systems are context-aware systems that use multi-modal data to improve the accuracy of natural language understanding as it is applied to spoken language input. Machine learning architectures are provided that jointly model spoken language input (“utterances”) and information displayed on a visual display (“on-screen information”). Such machine learning architectures can improve upon, and solve problems inherent in, existing spoken language understanding systems that operate in multi-modal contexts.