公开(公告)号：US20160350653A1

公开(公告)日：2016-12-01

申请号：US15170884

申请日：2016-06-01

Applicant: salesforce.com, inc.

Inventor： Richard Socher ,  Ankit Kumar ,  Ozan Irsoy ,  Mohit Iyyer ,  Caiming Xiong ,  Stephen Merity ,  Romain Paulus

IPC: G06N3/08 ,  G06F17/30 ,  G06N99/00

CPC classification number: G06N5/04 ,  G06N3/0445

Abstract: A novel unified neural network framework, the dynamic memory network, is disclosed. This unified framework reduces every task in natural language processing to a question answering problem over an input sequence. Inputs and questions are used to create and connect deep memory sequences. Answers are then generated based on dynamically retrieved memories.

Abstract translation: 公开了一种新颖的统一神经网络框架，动态存储网络。 这个统一框架将自然语言处理中的每个任务都减少到一个输入序列中的问题回答问题。 输入和问题用于创建和连接深层记忆序列。 然后基于动态检索的存储器生成答案。

公开(公告)号：US11113598B2

公开(公告)日：2021-09-07

申请号：US15221532

申请日：2016-07-27

Applicant: salesforce.com, inc.

Inventor： Richard Socher ,  Ankit Kumar ,  Ozan Irsoy ,  Mohit Iyyer ,  Caiming Xiong ,  Stephen Merity ,  Romain Paulus

IPC: G06N3/08 ,  G06N3/04 ,  G06F16/33 ,  G06F16/332

Abstract: A novel unified neural network framework, the dynamic memory network, is disclosed. This unified framework reduces every task in natural language processing to a question answering problem over an input sequence. Inputs and questions are used to create and connect deep memory sequences. Answers are then generated based on dynamically retrieved memories.

公开(公告)号：US20170024645A1

公开(公告)日：2017-01-26

申请号：US15221532

申请日：2016-07-27

Applicant: salesforce.com, inc.

Inventor： Richard Socher ,  Ankit Kumar ,  Ozan Irsoy ,  Mohit Iyyer ,  Caiming Xiong ,  Stephen Merity ,  Romain Paulus

IPC: G06N3/08 ,  G06N5/02

CPC classification number: G06N3/08 ,  G06F16/3329 ,  G06F16/3347 ,  G06N3/0427 ,  G06N3/0445

Abstract: A novel unified neural network framework, the dynamic memory network, is disclosed. This unified framework reduces every task in natural language processing to a question answering problem over an input sequence. Inputs and questions are used to create and connect deep memory sequences. Answers are then generated based on dynamically retrieved memories.

Abstract translation: 公开了一种新颖的统一神经网络框架，动态存储网络。 这个统一框架将自然语言处理中的每个任务都减少到一个输入序列中的问题回答问题。 输入和问题用于创建和连接深层记忆序列。 然后基于动态检索的存储器生成答案。