公开(公告)号：US11996083B2

公开(公告)日：2024-05-28

申请号：US17337518

申请日：2021-06-03

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Kaizhi Qian ,  Yang Zhang ,  Shiyu Chang ,  Jinjun Xiong ,  Chuang Gan ,  David Cox

IPC: G10L13/10 ,  G06N20/00 ,  G10L17/04 ,  G10L21/013 ,  G10L25/63

CPC classification number: G10L13/10 ,  G06N20/00 ,  G10L17/04 ,  G10L21/013 ,  G10L25/63

Abstract: A computer-implemented method is provided of using a machine learning model for disentanglement of prosody in spoken natural language. The method includes encoding, by a computing device, the spoken natural language to produce content code. The method further includes resampling, by the computing device without text transcriptions, the content code to obscure the prosody by applying an unsupervised technique to the machine learning model to generate prosody-obscured content code. The method additionally includes decoding, by the computing device, the prosody-obscured content code to synthesize speech indirectly based upon the content code.

公开(公告)号：US11657271B2

公开(公告)日：2023-05-23

申请号：US16658122

申请日：2019-10-20

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION ,  MASSACHUSETTS INSTITUTE OF TECHNOLOGY

Inventor： Shiyu Chang ,  Mo Yu ,  Yang Zhang ,  Tommi S. Jaakkola

IPC: G06N3/04 ,  G06N3/08 ,  G06K9/62

CPC classification number: G06N3/08 ,  G06N3/0454 ,  G06K9/6267 ,  G06N3/0445

Abstract: A method and system of determining an output label rationale are provided. A first generator receives a first class of data and selects one or more input features from the first class of data. A first predictor receives the one or more selected input features from the first generator and predicts a first output label. A second generator receives a second class of data and selects one or more input features from the second class of data. A second predictor receives the one or more selected input features from the second generator and predicts a second output label. A discriminator receives the first and second output labels and determines whether the selected one or more input features from the first class of data or the selected features of the one or more input features from the second class of data, more accurately represents the first output label.

公开(公告)号：US20210118088A1

公开(公告)日：2021-04-22

申请号：US17136805

申请日：2020-12-29

Applicant: International Business Machines Corporation

Inventor： Shiyu Chang ,  Liana L. Fong ,  Wei Tan

IPC: G06T1/60 ,  G06T1/20 ,  G06F17/16

Abstract: Techniques that facilitate matrix factorization associated with graphics processing units are provided. In one example, a computer-implemented method is provided. The computer-implemented method can comprise loading, by a graphics processing unit operatively coupled to a processor, item features from a data matrix into a shared memory. The data matrix can be a matrix based on one or more user features and item features. The computer-implemented method can further comprise tiling and aggregating, by the graphics processing unit, outer products of the data matrix tiles to generate an aggregate value and approximating, by the graphics processing unit, an update to a user feature of the data matrix based on the aggregate value and the loaded item features.

公开(公告)号：US20180232848A1

公开(公告)日：2018-08-16

申请号：US15432598

申请日：2017-02-14

Applicant: International Business Machines Corporation

Inventor： Shiyu Chang ,  Liana L. Fong ,  Wei Tan

IPC: G06T1/60 ,  G06T1/20

CPC classification number: G06T1/60 ,  G06F17/16 ,  G06T1/20

Abstract: Techniques that facilitate matrix factorization associated with graphics processing units are provided. In one example, a computer-implemented method is provided. The computer-implemented method can comprise loading, by a graphics processing unit operatively coupled to a processor, item features from a data matrix into a shared memory. The data matrix can be a matrix based on one or more user features and item features. The computer-implemented method can further comprise tiling and aggregating, by the graphics processing unit, outer products of the data matrix tiles to generate an aggregate value and approximating, by the graphics processing unit, an update to a user feature of the data matrix based on the aggregate value and the loaded item features.

公开(公告)号：US11790181B2

公开(公告)日：2023-10-17

申请号：US16997494

申请日：2020-08-19

Applicant: International Business Machines Corporation

Inventor： Xiaoxiao Guo ,  Mo Yu ,  Yupeng Gao ,  Chuang Gan ,  Shiyu Chang ,  Murray Scott Campbell

IPC: G06F40/35 ,  G06N3/08 ,  G06F40/295 ,  G06F40/253 ,  G06F40/284

CPC classification number: G06F40/35 ,  G06F40/253 ,  G06F40/284 ,  G06F40/295 ,  G06N3/08

Abstract: A current observation expressed in natural language is received. Entities in the current observation are extracted. A relevant historical observation is retrieved, which has at least one of the entities in common with the current observation. The current observation and the relevant historical observation are combined as observations. The observations and a template list specifying a list of verb phrases to be filled-in with at least some of the entities are input to a neural network, which can output the template list of the verb phrases filled-in with said at least some of the entities. The neural network can include attention mechanism. A reward associated with the neural network's output can be received and fed back to the neural network for retraining the neural network.

公开(公告)号：US20220392429A1

公开(公告)日：2022-12-08

申请号：US17337518

申请日：2021-06-03

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Kaizhi Qian ,  Yang Zhang ,  Shiyu Chang ,  Jinjun Xiong ,  Chuang Gan ,  David Cox

IPC: G10L13/10 ,  G06N20/00 ,  G10L21/013 ,  G10L17/04 ,  G10L25/63

Abstract: A computer-implemented method is provided of using a machine learning model for disentanglement of prosody in spoken natural language. The method includes encoding, by a computing device, the spoken natural language to produce content code. The method further includes resampling, by the computing device without text transcriptions, the content code to obscure the prosody by applying an unsupervised technique to the machine learning model to generate prosody-obscured content code. The method additionally includes decoding, by the computing device, the prosody-obscured content code to synthesize speech indirectly based upon the content code.

公开(公告)号：US20210117508A1

公开(公告)日：2021-04-22

申请号：US16658120

申请日：2019-10-20

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Shiyu Chang ,  Mo Yu ,  Yang Zhang ,  Tommi S. Jaakkola

IPC: G06F17/27 ,  G06F17/18 ,  G06K9/62 ,  G06N20/20 ,  G06N3/04 ,  G06N3/08

Abstract: A method and system of training a natural language processing network are provided. A corpus of data is received and one or more input features selected therefrom by a generator network. The one or more selected input features from the generator network are received by a first predictor network and used to predict a first output label. A complement of the selected input features from the generator network are received by a second predictor network and used to predict a second output label.

公开(公告)号：US20210034965A1

公开(公告)日：2021-02-04

申请号：US16530457

申请日：2019-08-02

Applicant: International Business Machines Corporation

Inventor： Ming Tan ,  Dakuo Wang ,  Mo Yu ,  Haoyu Wang ,  Yang Yu ,  Shiyu Chang ,  Saloni Potdar

IPC: G06N3/08 ,  G06N20/00 ,  G06F17/16

Abstract: A computer-implemented method includes using an embedding network to generate prototypical vectors. Each prototypical vector is based on a corresponding label associated with a first domain. The computer-implemented method also includes using the embedding network to generate an in-domain test vector based on at least one data sample from a particular label associated with the first domain and using the embedding network to generate an out-of-domain test vector based on at least one other data sample associated with a different domain. The computer-implemented method also includes comparing the prototypical vectors to the in-domain test vector to generate in-domain comparison values and comparing the prototypical vectors to the out-of-domain test vector to generate out-of-domain comparison values. The computer-implemented method also includes modifying, based on the in-domain comparison values and the out-of-domain comparison values, one or more parameters of the embedding network.

公开(公告)号：US10332234B2

公开(公告)日：2019-06-25

申请号：US15432598

申请日：2017-02-14

Applicant: International Business Machines Corporation

Inventor： Shiyu Chang ,  Liana L. Fong ,  Wei Tan

IPC: G06T1/20 ,  G06T1/60 ,  G06F17/16

Abstract: Techniques that facilitate matrix factorization associated with graphics processing units are provided. In one example, a computer-implemented method is provided. The computer-implemented method can comprise loading, by a graphics processing unit operatively coupled to a processor, item features from a data matrix into a shared memory. The data matrix can be a matrix based on one or more user features and item features. The computer-implemented method can further comprise tiling and aggregating, by the graphics processing unit, outer products of the data matrix tiles to generate an aggregate value and approximating, by the graphics processing unit, an update to a user feature of the data matrix based on the aggregate value and the loaded item features.

公开(公告)号：US20180232850A1

公开(公告)日：2018-08-16

申请号：US15842615

申请日：2017-12-14

Applicant: International Business Machines Corporation

Inventor： Shiyu Chang ,  Liana L. Fong ,  Wei Tan

IPC: G06T1/60 ,  G06T1/20

CPC classification number: G06T1/60 ,  G06F17/16 ,  G06T1/20

Abstract: Techniques that facilitate matrix factorization associated with graphics processing units are provided. In one example, a computer-implemented method is provided. The computer-implemented method can comprise loading, by a graphics processing unit operatively coupled to a processor, item features from a data matrix into a shared memory. The data matrix can be a matrix based on one or more user features and item features. The computer-implemented method can further comprise tiling and aggregating, by the graphics processing unit, outer products of the data matrix tiles to generate an aggregate value and approximating, by the graphics processing unit, an update to a user feature of the data matrix based on the aggregate value and the loaded item features.