Invention Grant
- Patent Title: Grounded text generation
-
Application No.: US18334065Application Date: 2023-06-13
-
Publication No.: US12131123B2Publication Date: 2024-10-29
- Inventor: Michel Galley , Christopher Brian Quirk , William Brennan Dolan , Zeqiu Wu
- Applicant: Microsoft Technology Licensing, LLC
- Applicant Address: US WA Redmond
- Assignee: Microsoft Technology Licensing, LLC
- Current Assignee: Microsoft Technology Licensing, LLC
- Current Assignee Address: US WA Redmond
- Agency: Alleman Hall & Tuttle LLP
- Main IPC: G06F40/30
- IPC: G06F40/30 ; G06F3/16 ; G06N20/00 ; H04L51/42

Abstract:
A controllable grounded response generation framework includes a machine learning model, a grounding interface, and a control interface. The machine learning model is trained to output computer-generated text based on input text. The grounding interface is useable by the machine learning model to access a grounding source including information related to the input text. The control interface is useable by the machine learning model to recognize a control signal. The machine learning model is configured to include information from the grounding source in the computer-generated text and focus the computer-generated text based on the control signal.
Public/Granted literature
- US20230325603A1 GROUNDED TEXT GENERATION Public/Granted day:2023-10-12
Information query