公开(公告)号：US20220164520A1

公开(公告)日：2022-05-26

申请号：US17146133

申请日：2021-01-11

Applicant: Microsoft Technology Licensing, LLC

Inventor： William B. DOLAN ,  Zeqiu WU ,  Michel GALLEY ,  Yizhe ZHANG ,  Zhang LI ,  Christopher John BROCKETT

IPC: G06F40/106 ,  G06F40/18 ,  G06N20/00

Abstract: Systems and method directed to assistive document generation are described. More specifically, similar documents share large portions of reusable text structures that can be used to generate an initial document thereby saving a user time. To generate the document, an indication to create the document may be received and based on the indication, a plurality of example documents and grounding content may be identified. Example documents may be existing documents that are similar to a target document of the writer. Grounding information may refer to content that is relevant, timely, and accurate when applied to the target document. The plurality of example documents and the grounding content may be received, and a document sketch based on the example documents and the grounding content may be generated and contains a plurality of predicted text sequences based on the example documents and the grounding content.

公开(公告)号：US20250036881A1

公开(公告)日：2025-01-30

申请号：US18919245

申请日：2024-10-17

Applicant: Microsoft Technology Licensing, LLC

Inventor： Michel GALLEY ,  Christopher Brian QUIRK ,  William Brennan DOLAN ,  Zeqiu WU

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.

公开(公告)号：US20230325603A1

公开(公告)日：2023-10-12

申请号：US18334065

申请日：2023-06-13

Applicant: Microsoft Technology Licensing, LLC

Inventor： Michel GALLEY ,  Christopher Brian QUIRK ,  William Brennan DOLAN ,  Zeqiu WU

IPC: G06F40/30 ,  G06F3/16 ,  G06N20/00 ,  H04L51/42

CPC classification number: G06F40/30 ,  G06F3/167 ,  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.

公开(公告)号：US20210192140A1

公开(公告)日：2021-06-24

申请号：US16817124

申请日：2020-03-12

Applicant: Microsoft Technology Licensing, LLC

Inventor： Michel GALLEY ,  Christopher Brian QUIRK ,  William Brennan DOLAN ,  Zeqiu WU

IPC: G06F40/30 ,  G06N20/00 ,  H04L12/58 ,  G06F3/16

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.