-
公开(公告)号：US20190251431A1
公开(公告)日：2019-08-15
申请号：US15974075
申请日：2018-05-08
Applicant: salesforce.com, inc.
Inventor： Nitish Shirish Keskar , Bryan McCann , Caiming Xiong , Richard Socher
CPC classification number: G06N3/08 , G06F17/2785 , G06F17/2881 , G06N3/0445 , G06N3/0454 , G06N5/04
Abstract: Approaches for multitask learning as question answering include a method for training that includes receiving a plurality of training samples including training samples from a plurality of task types, presenting the training samples to a neural model to generate an answer, determining an error between the generated answer and the natural language ground truth answer for each training sample presented, and adjusting parameters of the neural model based on the error. Each of the training samples includes a natural language context, question, and ground truth answer. An order in which the training samples are presented to the neural model includes initially selecting the training samples according to a first training strategy and switching to selecting the training samples according to a second training strategy. In some embodiments the first training strategy is a sequential training strategy and the second training strategy is a joint training strategy.
-
公开(公告)号：US20190251179A1
公开(公告)日：2019-08-15
申请号：US16395074
申请日：2019-04-25
Applicant: International Business Machines Corporation
Inventor： Joy Mustafi , Krishma Singla
IPC: G06F17/28 , G06K9/00 , G06F16/332
CPC classification number: G06F17/2881 , G06F16/3329 , G06K9/00476
Abstract: A computer-implemented method for language generation of a flow diagram, which receives a flow diagram. A plurality of geometric shapes within the flow diagram is identified. A plurality of text elements within the flow diagram is identified. The plurality of text elements and corresponding geometric shapes are associated. The association between the plurality of geometric shapes are identified. A diagram matrix based on the associations between the plurality of geometric shapes is generated. A linear language representation of the diagram matrix is generated.
-
公开(公告)号：US20190197122A1
公开(公告)日：2019-06-27
申请号：US16158925
申请日：2018-10-12
Inventor： Xi SHI , Shiliang DIAO , Sijiao CHEN , Yu LUO
CPC classification number: G06F17/2881 , G06F17/2785 , G06F17/2845
Abstract: The present disclosure provides a method and a device for generating a review article of hot news, and a terminal device. By way of example, the method may include: determining hot news based on reading feedback information and publishing time of respective news in a current webpage library; obtaining review data corresponding to the hot news; selecting a target review set from the review data based on a preset high-quality review model; and generating the review article based on the hot news and the target review set corresponding to the hot news.
-
公开(公告)号：US20180349361A1
公开(公告)日：2018-12-06
申请号：US15967453
申请日：2018-04-30
Applicant: Arria Data2Text Limited
Inventor： Gowri SRIPADA
IPC: G06F17/28
CPC classification number: G06F17/2881
Abstract: A method, apparatus, and computer program product for describing motion. The method may include receiving a set of eventualities (114). The set of eventualities (114) may describe at least one of a domain event and a domain state. The at least one of the domain event and the domain state may be derived from a set of spatio-temporal data (102) and the set of eventualities (114) may be associated with a particular region and a particular time period. The method may include organizing the set of eventualities to generate a document plan. The method may further include generating, using a processor, a linguistic representation of the set of eventualities using the document plan.
-
公开(公告)号：US20180342060A1
公开(公告)日：2018-11-29
申请号：US15690752
申请日：2017-08-30
Applicant: Enlitic, Inc.
Inventor： Li Yao , Devon Bernard , Kevin Lyman , Diogo Almeida , Jeremy Howard
CPC classification number: G16H30/40 , A61B5/002 , A61B5/0022 , A61B6/032 , A61B6/4233 , A61B6/463 , A61B6/468 , A61B6/50 , A61B6/503 , A61B6/505 , A61B6/5217 , A61B6/5288 , A61B6/5294 , A61B6/563 , A61B8/468 , A61B8/5223 , A61B8/565 , G01T1/247 , G06F3/048 , G06F3/04842 , G06F3/0485 , G06F3/167 , G06F17/2288 , G06F17/241 , G06F17/2765 , G06F17/2785 , G06F17/2795 , G06F17/2881 , G06F19/321 , G06F19/328 , G06F19/3418 , G06K9/03 , G06K9/6202 , G06K9/6215 , G06K9/6256 , G06K9/6267 , G06K2209/05 , G06N3/04 , G06N3/084 , G06Q10/10 , G06Q10/103 , G06Q50/22 , G06T7/0012 , G06T7/0016 , G06T7/11 , G06T11/003 , G06T11/60 , G06T2200/24 , G06T2207/10081 , G06T2207/10088 , G06T2207/10104 , G06T2207/10116 , G06T2207/10132 , G06T2207/20081 , G06T2207/30004 , G06T2207/30061 , G06T2207/30068 , G16H10/60 , G16H15/00 , G16H40/20 , G16H40/63 , G16H50/20 , G16H50/30 , G16H50/50 , H04L67/12 , H04L67/42 , H04N5/32
Abstract: A medical scan image analysis system is operable to receive a plurality of medical scans that represent a three-dimensional anatomical region and include a plurality of cross-sectional image slices. A plurality of three-dimensional subregions corresponding to each of the plurality of medical scans are generated by selecting a proper subset of the plurality of cross-sectional image slices from each medical scan, and by further selecting a two-dimensional subregion from each proper subset of cross-sectional image slices. A learning algorithm is performed on the plurality of three-dimensional subregions to generate a fully convolutional neural network. Inference data corresponding to a new medical scan received via the network is generated by performing an inference algorithm on the new medical scan by utilizing the fully convolutional neural network. An inferred abnormality is identified in the new medical scan based on the inference data.
-
公开(公告)号：US20180336903A1
公开(公告)日：2018-11-22
申请号：US15601542
申请日：2017-05-22
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Christopher M. Durham , Anne E. Gattiker , Thomas S. Hubregsten , Inseok Hwang , Jinho Lee
CPC classification number: G10L17/02 , G06F17/2785 , G06F17/279 , G06F17/2881 , G10L15/1822 , G10L15/22 , G10L15/28 , G10L25/27
Abstract: An apparatus comprising a memory and a processor coupled to the memory. The processor receives input from a user, processes a first portion of the input via more than one service module while receiving a second portion of the input to determine a first speculative result, wherein processing the first portion of the input comprises executing at least one service module coupled to a corresponding speculation buffer, processes a second portion of the input via the more than one service module to determine a second speculative result, wherein processing the second portion of the input comprises executing the at least one service module coupled to the corresponding speculation buffer, processes the input via the more than one service module to determine a final output, wherein processing the input comprises executing the at least one service module coupled to the corresponding speculation buffer, and outputs the final output to the user.
-
公开(公告)号：US20180278553A1
公开(公告)日：2018-09-27
申请号：US15756208
申请日：2016-09-01
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Seung-hak YU , Eun-jeong KO , Deok-ho KIM , Hae-jun LEE
IPC: H04L12/58 , H04W4/12 , G06F3/0482
CPC classification number: H04L51/02 , G06F3/0481 , G06F3/0482 , G06F3/0488 , G06F17/2241 , G06F17/271 , G06F17/278 , G06F17/2785 , G06F17/2881 , H04W4/12
Abstract: Provided are a device for transmitting an answer message including a display configured to display information, a communicator configured to receive a question message from another device, a processor configured to control the display to display graphics representing a plurality of pieces of recommendation information which are includable in an answer message for the received question message and relations between the plurality of pieces of recommendation information, and a user input unit configured to receive a user input that selects at least one of the plurality of pieces of recommendation information, wherein the communicator is further configured to transmit an answer message including the selected recommendation information to the another device according to the user input.
-
公开(公告)号：US20180220000A1
公开(公告)日：2018-08-02
申请号：US15940113
申请日：2018-03-29
Applicant: Google LLC
Inventor： Eyal Segalis , Daniel Walevski , Yaniv Leviathan
CPC classification number: H04M3/4936 , G06F17/27 , G06F17/2705 , G06F17/2881 , G06N20/00 , G06Q10/06 , G06Q10/10 , G10L13/08 , G10L15/005 , G10L15/1807 , G10L15/1815 , G10L15/222 , G10L25/63 , G10L2015/227 , H04M3/42042 , H04M3/42093 , H04M3/493 , H04M3/58 , H04M3/60 , H04M2242/18
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, relating to synthetic call status updates. In some implementations, a method includes determining, by a task manager module, that a triggering event has occurred to provide a current status of a user call request. The method may then determine, by the task manager module, the current status of the user call request. A representation of the current status of the user call request is generated. Then, the generated representation of the current status of the user call request is provided to the user.
-
公开(公告)号：US20180210874A1
公开(公告)日：2018-07-26
申请号：US15415506
申请日：2017-01-25
Applicant: Google LLC.
Inventor： Ariel FUXMAN , Vivek RAMAVAJJALA , Ning YE , John Patrick McGregor, JR.
CPC classification number: G06F17/2785 , G06F17/276 , G06F17/279 , G06F17/2881 , G06K9/481 , G06N3/0445 , G06N3/0454
Abstract: Implementations relate to automatic response suggestions to images included in received messages. In some implementations, a computer-implemented method includes detecting an image posted within a first message by a first user, and programmatically analyzing the image to determine a feature vector representative of the image. The method programmatically generates one or more suggested responses to the first message based on the feature vector, each suggested response being a conversational reply to the first message. Generating the suggested responses includes determining probabilities associated with word sequences for the feature vector using a model trained with previous responses to previous images, and selecting one or more of the word sequences based on the associated probabilities. The suggested responses are determined based on the selected word sequences. The method causes the suggested responses to be rendered in the messaging application as one or more suggestions to a second user.
-
公开(公告)号：US10026274B2
公开(公告)日：2018-07-17
申请号：US15421921
申请日：2017-02-01
Applicant: ARRIA DATA2TEXT LIMITED
Inventor： Ehud B. Reiter
IPC: G08B3/00 , G08B5/00 , G08B7/00 , G08B5/36 , G08B23/00 , G06F17/28 , G08B5/22 , G06F17/22 , G06F19/00 , G06F17/24 , G06F17/27
CPC classification number: G08B5/36 , G06F17/2247 , G06F17/248 , G06F17/27 , G06F17/2881 , G06F19/00 , G06F19/30 , G08B5/22 , G08B7/06 , G08B21/0453 , G08B23/00 , G08B29/18 , G16H15/00 , G16H50/20 , G16H50/30 , G16H50/70 , G16H70/00
Abstract: Methods, apparatuses, and computer program products are described herein that are configured to enable validation of an alert condition. In some example embodiments, a method is provided that comprises detecting an alert condition. The method of this embodiment may also include generating a set of messages based on one or more key events in a primary data channel and one or more significant events in one or more related data channels in response to the alert condition. The method of this embodiment may also include determining a validity of the alert condition based on the set of messages that express the one or more key events, the one or more significant events, a relationship between the one or more key events and the one or more significant events, an alert context and the one or causes of the alert condition.
