公开(公告)号：US10699078B2

公开(公告)日：2020-06-30

申请号：US15578195

申请日：2015-05-29

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： Furu Wei ,  Ming Zhou ,  Yang Liu ,  Ziqiang Cao ,  Shaohan Huang ,  Li Dong ,  Lei Cui

IPC: G06F17/27 ,  G06F17/24 ,  G06F40/295 ,  G06F40/134 ,  G06F40/169 ,  G06F40/216 ,  G06F3/048

Abstract: Methods and systems for providing a comments-centered news reader. Configurations allow live comments to be presented along with the news or similar website content. While a user scrolls up and down in a browser presenting a news article on the user's computer device (e.g., mobile device), linked comments are shown in a selected region. The displayed comments automatically change to adapt to what parts (paragraphs, sentences) of the news article that user is currently reading. At the same time, users can publish their own comments without having to proceed to a separate section of the browser, thus saving the viewer actions and improving the user's experience. The user's system or a remote server records the comments along with the article or the place users are in the article when the comment was entered.

公开(公告)号：US12260338B2

公开(公告)日：2025-03-25

申请号：US17005067

申请日：2020-08-27

Applicant: Microsoft Technology Licensing, LLC

Inventor： Jian Jiao ,  Yeyun Gong ,  Nan Duan ,  Ruofei Zhang ,  Ming Zhou

IPC: G06N3/088 ,  G06N3/045 ,  G06N3/063

Abstract: A transformer-based neural network includes at least one mask attention network (MAN). The MAN computes an original attention data structure that expresses influence between pairs of data items in a sequence of data items. The MAN then modifies the original data structure by mask values in a mask data structure, to produce a modified attention data structure. Compared to the original attention data structure, the modified attention data structure better accounts for the influence of neighboring data items in the sequence of data items, given a particular data item under consideration. The mask data structure used by the MAN can have static and/or machine-trained mask values. In one implementation, the transformer-based neural network includes at least one MAN in combination with at least one other attention network that does not use a mask data structure, and at least one feed-forward neural network.

公开(公告)号：US20250086406A1

公开(公告)日：2025-03-13

申请号：US18801211

申请日：2024-08-12

Applicant: Microsoft Technology Licensing, LLC

Inventor： Nan Duan ,  Ming Zhou ,  Yaobo Liang

IPC: G06F40/42 ,  G06F40/30

Abstract: Implementations of the present disclosure relate to text generation with a customizable style. In a method, a first natural language is received; the first natural language text is converted, via a text generation model, into a second natural language text that at least partly reflects the meaning of the first natural language text and has a style distinguishable from the first natural language text, the text generation model comprising a modifiable parameter; and in response to receiving a modification to the parameter, the first natural language text is converted, via the text generation model, into a third natural language text that at least partly reflects the meaning of the first natural language text and includes a style distinguishable from both the first natural language text and the second natural language text.

公开(公告)号：US11693894B2

公开(公告)日：2023-07-04

申请号：US17355256

申请日：2021-06-23

Applicant: Microsoft Technology Licensing, LLC

Inventor： Nan Duan ,  Ming Zhou

IPC: G06F16/332 ,  G06F40/279 ,  G06F16/33 ,  H04L51/02 ,  G06F16/00

CPC classification number: G06F16/3329 ,  G06F16/00 ,  G06F16/334 ,  G06F40/279 ,  H04L51/02

Abstract: In implementations of the subject matter described herein, a new approach for presenting a response to a message in a conversation is proposed. Generally speaking, in response to receiving a message in a conversation, the received message will be matched with one or more documents on the sentence basis. That is, the received message is compared with the sentences from a document(s), rather than predefined query-response pairs. In this way, a whole sentence may be selected from the document as a candidate response. Then the suitability of this sentence with respect to the ongoing conversation will be determined, and the response will be generated and rendered in an adaptive way based on the suitability. As a result, the user experiences may be significantly enhanced in the chatbot scenario.

公开(公告)号：US11544474B2

公开(公告)日：2023-01-03

申请号：US16765335

申请日：2018-12-06

Applicant: Microsoft Technology Licensing, LLC

Inventor： Nan Duan ,  Yuanhua Lv ,  Ming Zhou ,  Duyu Tang

IPC: G06F40/126 ,  G06F40/284 ,  G06F40/40 ,  G06F16/25 ,  G06F40/279 ,  G06F40/177 ,  G06N3/04 ,  G06N3/08

Abstract: Implementations of the subject matter described herein provide a solution for generating a text from the structured data. In this solution, the structured data is converted into its representation, where the structured data comprises a plurality of cells, and the representation of the structured data comprises plurality of representations of the plurality of cells. A natural language sentence associated with the structured data may be determined based on the representation of the structured data, thereby implementing the function of converting the structured data into a text.

公开(公告)号：US10891322B2

公开(公告)日：2021-01-12

申请号：US15772472

申请日：2016-10-26

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： Ming Zhou ,  Yu-Ting Kuo ,  Furu Wei ,  Lei Cui ,  Shaohan Huang ,  Kati London ,  Wei-Ying Ma ,  Haoyong Zhang

IPC: G06F16/332 ,  G06F16/335 ,  G06F16/33 ,  G06F16/9535 ,  G06Q50/00 ,  G06F40/284 ,  G06K9/62

Abstract: An example environment can automatically generate content for a conversation in response to a presented content item. An example computing device receives information associated with a content item produced by a source system, the content item being accessible to other the computing devices via a network. In response to receiving the information, the computing device identifies a start comment. In response to identifying the start comment, the computing device identifies a reply to the start comment using at least a ranking model.

公开(公告)号：US12235898B2

公开(公告)日：2025-02-25

申请号：US18582092

申请日：2024-02-20

Applicant: Microsoft Technology Licensing, LLC

Inventor： Nan Duan ,  Lei Ji ,  Ming Zhou

IPC: G06F16/70 ,  G06F16/732 ,  G06F16/735 ,  G06F16/74 ,  G06F16/783

Abstract: The present disclosure provides a technical solution of multi-modal chatting, which may provide response to user query by using multi-modal response in the interaction between chatbot and human beings, so that the expressing ways and the expressed content by the chatbot could be richer by using such response in a multi-modal way.

公开(公告)号：US20240193208A1

公开(公告)日：2024-06-13

申请号：US18582092

申请日：2024-02-20

Applicant: Microsoft Technology Licensing, LLC

Inventor： Nan Duan ,  Lei Ji ,  Ming Zhou

IPC: G06F16/783 ,  G06F16/732 ,  G06F16/735 ,  G06F16/74

CPC classification number: G06F16/7834 ,  G06F16/732 ,  G06F16/735 ,  G06F16/745

Abstract: The present disclosure provides a technical solution of multi-modal chatting, which may provide response to user query by using multi-modal response in the interaction between chatbot and human beings, so that the expressing ways and the expressed content by the chatbot could be richer by using such response in a multi-modal way.

公开(公告)号：US11877016B2

公开(公告)日：2024-01-16

申请号：US17435354

申请日：2020-03-16

Applicant: Microsoft Technology Licensing, LLC

Inventor： Lei Cui ,  Furu Wei ,  Shaohan Huang ,  Ming Zhou

IPC: H04N21/234 ,  G06V10/74 ,  H04N21/233 ,  H04N21/235 ,  H04N21/488

CPC classification number: H04N21/23418 ,  G06V10/761 ,  H04N21/233 ,  H04N21/235 ,  H04N21/4884

Abstract: The present disclosure provides a technical solution of live comments generating, which may acquire candidate texts highly similar with segments of video as live comments of corresponding segments by matching the candidate texts with the segments, and further generate new live comments based on video segments and existed live comments to enrich the live comments information of related video.

公开(公告)号：US11727270B2

公开(公告)日：2023-08-15

申请号：US16799091

申请日：2020-02-24

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： Ji Li ,  Amit Srivastava ,  Xingxing Zhang ,  Furu Wei ,  Ming Zhou

IPC: G06F40/40 ,  G06N3/08 ,  G06F40/205 ,  G06F18/214 ,  G10L15/16 ,  G10L15/18 ,  G06N3/088 ,  G06F40/30

CPC classification number: G06N3/08 ,  G06F18/2148 ,  G06F40/205 ,  G06F40/40 ,  G06F40/30 ,  G06N3/088 ,  G10L15/16 ,  G10L15/18

Abstract: A method and system for training a text-to-content recommendation ML model includes training a first ML model using a first training data set, utilizing the trained first ML model to infer information about the data contained in the first training data set, collecting the inferred information to generate a second training data set, and utilizing the first training data set and the second training data set to train a second ML model. The second ML model may be a text-to-content recommendation ML model.