公开(公告)号：US11640527B2

公开(公告)日：2023-05-02

申请号：US16658399

申请日：2019-10-21

Applicant: salesforce.com, inc.

Inventor： Lichao Sun ,  Jia Li ,  Caiming Xiong ,  Yingbo Zhou

IPC: G06N3/08 ,  G06N3/04 ,  G06N3/082

Abstract: Systems and methods are provided for near-zero-cost (NZC) query framework or approach for differentially private deep learning. To protect the privacy of training data during learning, the near-zero-cost query framework transfers knowledge from an ensemble of teacher models trained on partitions of the data to a student model. Privacy guarantees may be understood intuitively and expressed rigorously in terms of differential privacy. Other features are also provided.

公开(公告)号：US20230113750A1

公开(公告)日：2023-04-13

申请号：US17498155

申请日：2021-10-11

Applicant: salesforce.com, inc.

Inventor： Lav Raj Varshney ,  Yingbo Zhou ,  Caiming Xiong ,  Govardana Sachithanandam Ramachandran

IPC: G06F11/26 ,  G06F11/36 ,  G06N20/00

Abstract: A system performs group testing on a population of items. The group testing identifies items satisfying particular criteria from a population of items, for example, defective items from the population. The group testing may be performed for software or hardware testing, for testing a human population, for training of deep learning applications, and so on. The system trains a machine learning based model, for example, a reinforcement learning based model to evaluate groups. The model may further determine system dynamics that may represent priors of items. An agent treats the population and groups of items being tested as the environment and performs actions, for example, adjusting the groups. The system also performs a non-adaptive strategy based on monte carlo simulation of tests based on a simulation results.

公开(公告)号：US20220129629A1

公开(公告)日：2022-04-28

申请号：US17161214

申请日：2021-01-28

Applicant: salesforce.com, inc.

Inventor： Tong Niu ,  Semih Yavuz ,  Yingbo Zhou ,  Nitish Shirish Keskar ,  Huan Wang ,  Caiming Xiong

IPC: G06F40/284 ,  G06F40/242 ,  G06K9/62 ,  G06N7/00

Abstract: Embodiments described herein provide dynamic blocking, a decoding algorithm which enables large-scale pretrained language models to generate high-quality paraphrases in an un-supervised setting. Specifically, in order to obtain an alternative surface form, when the language model emits a token that is present in the source sequence, the language model is prevented from generating the next token that is the same as the subsequent source token in the source sequence at the next time step. In this way, the language model is forced to generate a paraphrased sequence of the input source sequence, but with mostly different wording.

公开(公告)号：US11106182B2

公开(公告)日：2021-08-31

申请号：US16054935

申请日：2018-08-03

Applicant: salesforce.com, inc.

Inventor： Ehsan Hosseini-Asl ,  Caiming Xiong ,  Yingbo Zhou ,  Richard Socher

IPC: G05B13/02 ,  G06N3/02 ,  G10L21/003 ,  G10L15/065 ,  G10L15/07 ,  G06K9/62

Abstract: A method for training parameters of a first domain adaptation model includes evaluating a cycle consistency objective using a first task specific model associated with a first domain and a second task specific model associated with a second domain. The evaluating the cycle consistency objective is based on one or more first training representations adapted from the first domain to the second domain by a first domain adaptation model and from the second domain to the first domain by a second domain adaptation model, and one or more second training representations adapted from the second domain to the first domain by the second domain adaptation model and from the first domain to the second domain by the first domain adaptation model. The method further includes evaluating a learning objective based on the cycle consistency objective, and updating parameters of the first domain adaptation model based on learning objective.

公开(公告)号：US10783875B2

公开(公告)日：2020-09-22

申请号：US16027111

申请日：2018-07-03

Applicant: salesforce.com, inc.

Inventor： Ehsan Hosseini-Asl ,  Caiming Xiong ,  Yingbo Zhou ,  Richard Socher

IPC: G10L15/07 ,  G10L15/22 ,  G10L15/16 ,  G06N3/08

Abstract: A system for domain adaptation includes a domain adaptation model configured to adapt a representation of a signal in a first domain to a second domain to generate an adapted presentation and a plurality of discriminators corresponding to a plurality of bands of values of a domain variable. Each of the plurality of discriminators is configured to discriminate between the adapted representation and representations of one or more other signals in the second domain.

公开(公告)号：US10573295B2

公开(公告)日：2020-02-25

申请号：US15878113

申请日：2018-01-23

Applicant: salesforce.com, inc.

Inventor： Yingbo Zhou ,  Caiming Xiong

IPC: G10L15/06 ,  G10L15/16 ,  G06N3/04 ,  G06N3/08 ,  G06N7/00 ,  G10L15/14 ,  G10L25/51

Abstract: The disclosed technology teaches a deep end-to-end speech recognition model, including using multi-objective learning criteria to train a deep end-to-end speech recognition model on training data comprising speech samples temporally labeled with ground truth transcriptions. The multi-objective learning criteria updates model parameters of the model over one thousand to millions of backpropagation iterations by combining, at each iteration, a maximum likelihood objective function that modifies the model parameters to maximize a probability of outputting a correct transcription and a policy gradient function that modifies the model parameters to maximize a positive reward defined based on a non-differentiable performance metric which penalizes incorrect transcriptions in accordance with their conformity to corresponding ground truth transcriptions; and upon convergence after a final backpropagation iteration, persisting the modified model parameters learned by using the multi-objective learning criteria with the model to be applied to further end-to-end speech recognition.

公开(公告)号：US10542270B2

公开(公告)日：2020-01-21

申请号：US15874515

申请日：2018-01-18

Applicant: salesforce.com, inc.

Inventor： Yingbo Zhou ,  Luowei Zhou ,  Caiming Xiong ,  Richard Socher

IPC: H04N7/12 ,  H04N11/12 ,  H04N19/46 ,  H04N19/44 ,  H04N19/60 ,  H04N19/187 ,  H04N21/81 ,  H04N19/33 ,  H04N19/126 ,  H04N21/488 ,  H04N19/132

Abstract: Systems and methods for dense captioning of a video include a multi-layer encoder stack configured to receive information extracted from a plurality of video frames, a proposal decoder coupled to the encoder stack and configured to receive one or more outputs from the encoder stack, a masking unit configured to mask the one or more outputs from the encoder stack according to one or more outputs from the proposal decoder, and a decoder stack coupled to the masking unit and configured to receive the masked one or more outputs from the encoder stack. Generating the dense captioning based on one or more outputs of the decoder stack. In some embodiments, the one or more outputs from the proposal decoder include a differentiable mask. In some embodiments, during training, error in the dense captioning is back propagated to the decoder stack, the encoder stack, and the proposal decoder.

公开(公告)号：US11830477B2

公开(公告)日：2023-11-28

申请号：US16993797

申请日：2020-08-14

Applicant: salesforce.com, inc.

Inventor： Young Mo Kang ,  Yingbo Zhou

IPC: G10L15/00 ,  G10L15/06 ,  G10L15/26 ,  G10L15/16 ,  G10L15/08

CPC classification number: G10L15/063 ,  G10L15/16 ,  G10L15/26 ,  G10L2015/0631 ,  G10L2015/088

Abstract: An automatic speech recognition (ASR) system that determines a textual representation of a word from a word spoken in a natural language is provided. The ASR system uses an acoustic model, a language model, and a decoder. When the ASR system receives a spoken word, the acoustic model generates word candidates for the spoken word. The language model determines an n-gram score for each word candidate. The n-gram score includes a base score and a bias score. The bias score is based on a logarithmic probability of the word candidate, where the logarithmic probability is derived using a class-based language model where the words are clustered into non-overlapping clusters according to word statistics. The decoder decodes a textual representation of the spoken word from the word candidates and the corresponding n-gram score for each word candidate.

公开(公告)号：US20230229957A1

公开(公告)日：2023-07-20

申请号：US17576724

申请日：2022-01-14

Applicant: salesforce.com, inc.

Inventor： Shuyang Li ,  Yingbo Zhou ,  Semih Yavuz ,  Govardana Sachithanandam Ramachandran

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: Methods, apparatuses, and computer-program products are disclosed. The method may include inputting one or more subcomponent training datasets into the plurality of subcomponent models of the machine learning model, the machine learning model may be configured to perform a final task, and the plurality of subcomponent models may be configured to perform sequential subtasks that result in the final task. The method may include computing one or more weights for data points of the one or more subcomponent training datasets and the one or more weights may be based on a contribution of the data points to an end-to-end error loss measurement associated with performing the final task of the machine learning model. The method may include training the plurality of subcomponent models based on the one or more weights for the data points of the one or more subcomponent training datasets.

公开(公告)号：US11625436B2

公开(公告)日：2023-04-11

申请号：US17119941

申请日：2020-12-11

Applicant: salesforce.com, inc.

Inventor： Young Mo Kang ,  Wenhao Liu ,  Yingbo Zhou

IPC: G06F16/90 ,  G06F16/9032 ,  G06F16/901 ,  G06F40/274 ,  G06N3/02 ,  G06F11/34 ,  G06K9/62 ,  G06F40/284 ,  G06F16/903 ,  G06F40/44

Abstract: Embodiments described herein provide a query autocompletion (QAC) framework at subword level. Specifically, the QAC framework employs a subword encoder that encodes or converts the sequence of input alphabet letters into a sequence of output subwords. The generated subword candidate sequences from the subword encoder is then for the n-gram language model to perform beam search on. For example, as user queries for search engines are in general short, e.g., ranging from 10 to 30 characters. The n-gram language model at subword level may be used for modeling such short contexts and outperforms the traditional language model in both completion accuracy and runtime speed. Furthermore, key computations are performed prior to the runtime to prepare segmentation candidates in support of the subword encoder to generate subword candidate sequences, thus eliminating significant computational overhead.