Invention Grant
- Patent Title: Utilizing a dynamic memory network for state tracking
-
Application No.: US17135629Application Date: 2020-12-28
-
Publication No.: US11657802B2Publication Date: 2023-05-23
- Inventor: Seokhwan Kim , Walter Chang
- Applicant: Adobe Inc.
- Applicant Address: US CA San Jose
- Assignee: Adobe Inc.
- Current Assignee: Adobe Inc.
- Current Assignee Address: US CA San Jose
- Agency: Keller Preece PLLC
- Main IPC: G10L21/00
- IPC: G10L21/00 ; G10L25/00 ; G10L15/16 ; G06F16/9032 ; G10L15/22 ; H04L51/02

Abstract:
The present disclosure relates to generating digital responses based on digital dialog states generated by a neural network having a dynamic memory network architecture. For example, in one or more embodiments, the disclosed system provides a digital dialog having one or more segments to a dialog state tracking neural network having a dynamic memory network architecture that includes a set of multiple memory slots. In some embodiments, the dialog state tracking neural network further includes update gates and reset gates used in modifying the values stored in the memory slots. For instance, the disclosed system can utilize cross-slot interaction update/reset gates to accurately generate a digital dialog state for each of the segments of digital dialog. Subsequently, the system generates a digital response for each segment of digital dialog based on the digital dialog state.
Public/Granted literature
- US20210118430A1 UTILIZING A DYNAMIC MEMORY NETWORK FOR STATE TRACKING Public/Granted day:2021-04-22
Information query