公开(公告)号：WO2022108671A1

公开(公告)日：2022-05-27

申请号：PCT/US2021/053454

申请日：2021-10-05

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

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

IPC: G06F3/0482 ,  G06F40/186

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：WO2022271357A1

公开(公告)日：2022-12-29

申请号：PCT/US2022/030156

申请日：2022-05-20

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： DOLAN, William B. ,  GALLEY, Michel ,  ZHANG, Yizhe ,  BROCKETT, Christopher John

IPC: G06F40/166 ,  G06F40/56 ,  G06F40/44 ,  G06F40/169 ,  G06F3/0481 ,  G06F3/0484 ,  G06F40/30 ,  G06F40/40

Abstract: Aspects of the present disclosure relate to techniques for interactive content generation. In examples, processed content may be produced by a generative model based on a content seed, such as a sentence or paragraph. User input associated with the processed content may be received, for example to revise the processed content or provide additional input with respect to a subpart of the processed content that is associated with a low confidence score. A generative model may produce updated processed content based at least in part on the previously processed content, the user input, and/or, in some examples, additional content, as may be indicated by a user. Thus, a user may iterate on processed content that is produced by such generative models through successive interactions, thereby enabling the user to provide input to the generative model as part of the content generation process.

公开(公告)号：WO2021126388A1

公开(公告)日：2021-06-24

申请号：PCT/US2020/058995

申请日：2020-11-05

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

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

IPC: G06N20/00 ,  G06N3/04 ,  G06F40/56 ,  G06N3/08 ,  G06N3/00 ,  G06F3/167 ,  G06F40/30 ,  G06F40/35 ,  G06N3/006 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/088 ,  H04L51/22

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：WO2016195912A1

公开(公告)日：2016-12-08

申请号：PCT/US2016/031082

申请日：2016-05-06

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： GALLEY, Michel ,  SORDONI, Alessandro ,  BROCKETT, Christopher John ,  GAO, Jianfeng ,  DOLAN, William Brennan ,  JI, Yangfeng ,  AULI, Michael ,  MITCHELL, Margaret Ann ,  NIE, Jian-Yun

IPC: G06F17/28

CPC classification number: H04L51/02 ,  G06F17/2881 ,  G06N3/0445 ,  G06N3/0454

Abstract: Examples are generally directed towards context-sensitive generation of conversational responses. Context-message-response n-tuples are extracted from at least one source of conversational data to generate a set of training context-message-response n-tuples. A response generation engine is trained on the set of training context-message-response n-tuples. The trained response generation engine automatically generates a context-sensitive response based on a user generated input message and conversational context data. A digital assistant utilizes the trained response generation engine to generate context-sensitive, natural language responses that are pertinent to user queries.

Abstract translation: 实例通常针对上下文敏感的会话响应的生成。 从至少一个会话数据源提取上下文消息响应n元组，以生成一组训练上下文消息响应n元组。 在一组训练上下文 - 消息响应n元组上训练响应生成引擎。 经过训练的响应生成引擎基于用户生成的输入消息和对话上下文数据自动生成上下文敏感的响应。 数字助理利用经过训练的响应生成引擎来生成与用户查询相关的上下文相关的自然语言响应。

公开(公告)号：WO2016195911A1

公开(公告)日：2016-12-08

申请号：PCT/US2016/031081

申请日：2016-05-06

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： GALLEY, Michel ,  SORDONI, Alessandro ,  BROCKETT, Christopher John ,  GAO, Jianfeng ,  DOLAN, William Brennan ,  JI, Yangfeng ,  AULI, Michael ,  MITCHELL, Margaret Ann ,  QUIRK, Christopher Brian

IPC: G06F17/28

CPC classification number: H04L51/02 ,  G06F17/2881 ,  H04L51/10 ,  H04L51/26

Abstract: Examples are generally directed towards automatic assessment of machine generated conversational responses. Context-message-response n-tuples are extracted from at least one source of conversational data to generate a set of multi-reference responses. A response in the set of multi-reference responses includes a context-message data pair and rating. The rating indicates a quality of the response relative to the context-message data pair. A response assessment engine generates a metric score for a machine-generated response based on an assessment metric and the set of multi-reference responses. The metric score indicates a quality of the machine-generated conversational response relative to a user-generated message and a context of the user-generated message. A response generation system of a computing device, such as a digital assistant, is optimized and adjusted based on the metric score to improve the accuracy, quality, and relevance of responses output to the user.

Abstract translation: 实例通常针对机器生成的会话响应的自动评估。 从至少一个会话数据源提取上下文消息响应n元组，以生成一组多参考响应。 多参考响应集中的响应包括上下文消息数据对和评级。 该等级表示相对于上下文消息数据对的响应的质量。 响应评估引擎基于评估度量和多参考响应的集合生成机器生成的响应的度量得分。 度量得分表示相对于用户生成的消息和用户生成的消息的上下文的机器生成的会话响应的质量。 基于度量分数优化和调整诸如数字助理的计算设备的响应生成系统，以提高对用户输出的响应的准确性，质量和相关性。