中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

20 records (took 0.029 seconds)

    TRAINING OF NEURAL NETWORK BASED NATURAL LANGUAGE PROCESSING MODELS USING DENSE KNOWLEDGE DISTILLATION
    11.
    发明申请
    TRAINING OF NEURAL NETWORK BASED NATURAL LANGUAGE PROCESSING MODELS USING DENSE KNOWLEDGE DISTILLATION 有权

    公开(公告)号：US20210182662A1

    公开(公告)日：2021-06-17

    申请号：US16717698

    申请日：2019-12-17

    Applicant: Adobe Inc.

    Inventor： Tuan Manh Lai ,  Trung Huu Bui ,  Quan Hung Tran

    IPC: G06N3/08 ,  G06N3/04 ,  G06F40/284

    Abstract: Techniques for training a first neural network (NN) model using a pre-trained second NN model are disclosed. In an example, training data is input to the first and second models. The training data includes masked tokens and unmasked tokens. In response, the first model generates a first prediction associated with a masked token and a second prediction associated with an unmasked token, and the second model generates a third prediction associated with the masked token and a fourth prediction associated with the unmasked token. The first model is trained, based at least in part on the first, second, third, and fourth predictions. In another example, a prediction associated with a masked token, a prediction associated with an unmasked token, and a prediction associated with whether two sentences of training data are adjacent sentences are received from each of the first and second models. The first model is trained using the predictions.

    GENERATING AND UTILIZING CLASSIFICATION AND QUERY-SPECIFIC MODELS TO GENERATE DIGITAL RESPONSES TO QUERIES FROM CLIENT DEVICE
    12.
    发明申请
    GENERATING AND UTILIZING CLASSIFICATION AND QUERY-SPECIFIC MODELS TO GENERATE DIGITAL RESPONSES TO QUERIES FROM CLIENT DEVICE 审中-公开

    公开(公告)号：US20190325068A1

    公开(公告)日：2019-10-24

    申请号：US15957556

    申请日：2018-04-19

    Applicant: Adobe Inc.

    Inventor： Tuan Manh Lai ,  Trung Bui ,  Sheng Li ,  Quan Hung Tran ,  Hung Bui

    IPC: G06F17/30 ,  G06N3/08 ,  G06Q30/06

    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating digital responses to digital queries by utilizing a classification model and query-specific analysis models. For example, the disclosed systems can train a classification model to generate query classifications corresponding to product queries, conversational queries, and/or recommendation/purchase queries. Moreover, the disclosed systems can apply the classification model to select pertinent models for particular queries. For example, upon classifying a product query, disclosed systems can utilize a neural ranking model (trained based on a set of training product specifications and training queries) to generate relevance scores for product specifications associated with a digital query. The disclosed systems can further compare generated relevance scores to select a product specification and generate a digital response that includes the pertinent product specification to provide for display to a client device.

    POSITION-BASED TEXT-TO-SPEECH MODEL
    13.
    发明申请
    POSITION-BASED TEXT-TO-SPEECH MODEL 有权

    公开(公告)号：US20250095631A1

    公开(公告)日：2025-03-20

    申请号：US18528116

    申请日：2023-12-04

    Applicant: Adobe Inc.

    Inventor： Puneet Mathur ,  Franck Dernoncourt ,  Quan Hung Tran ,  Jiuxiang Gu ,  Ani Nenkova ,  Vlad Ion Morariu ,  Rajiv Bhawanji Jain ,  Dinesh Manocha

    IPC: G10L13/08 ,  G10L13/04 ,  G10L13/06 ,  G10L25/18

    Abstract: Position-based text-to-speech model and training techniques are described. A digital document, for instance, is received by an audio synthesis service. A text-to-speech model is utilized by the audio synthesis service to generate digital audio from text included in the digital document. The text-to-speech model, for instance, is configured to generate a text encoding and a document positional encoding from an initial text sequence of the digital document. The document positional encoding is based on a location of the text encoding within the digital document. Digital audio is then generated by the text-to-speech model that includes a spectrogram having a reordered text sequence, which is different from the initial text sequence, by decoding the text encoding and the document positional encoding.

    SYSTEMS AND METHODS FOR DATA CORRECTION
    16.
    发明公开
    SYSTEMS AND METHODS FOR DATA CORRECTION 审中-公开

    公开(公告)号：US20240135165A1

    公开(公告)日：2024-04-25

    申请号：US18047335

    申请日：2022-10-18

    Applicant: ADOBE INC.

    Inventor： Varun Manjunatha ,  Sarthak Jain ,  Rajiv Bhawanji Jain ,  Ani Nenkova Nenkova ,  Christopher Alan Tensmeyer ,  Franck Dernoncourt ,  Quan Hung Tran ,  Ruchi Deshpande

    IPC: G06N3/08 ,  G06F40/295

    CPC classification number: G06N3/08 ,  G06F40/295

    Abstract: One aspect of systems and methods for data correction includes identifying a false label from among predicted labels corresponding to different parts of an input sample, wherein the predicted labels are generated by a neural network trained based on a training set comprising training samples and training labels corresponding to parts of the training samples; computing an influence of each of the training labels on the false label by approximating a change in a conditional loss for the neural network corresponding to each of the training labels; identifying a part of a training sample of the training samples and a corresponding source label from among the training labels based on the computed influence; and modifying the training set based on the identified part of the training sample and the corresponding source label to obtain a corrected training set.

    INTENT DETECTION
    18.
    发明申请
    INTENT DETECTION 有权

    公开(公告)号：US20230136527A1

    公开(公告)日：2023-05-04

    申请号：US17453562

    申请日：2021-11-04

    Applicant: ADOBE INC.

    Inventor： Jianguo Zhang ,  Trung Huu Bui ,  Seunghyun Yoon ,  Xiang Chen ,  Quan Hung Tran ,  Walter W. Chang

    IPC: G06F40/40 ,  G06F40/30 ,  G06F40/284 ,  G06V30/19

    Abstract: Systems and methods for natural language processing are described. One or more aspects of a method, apparatus, and non-transitory computer readable medium include receiving a text phrase; encoding the text phrase using an encoder to obtain a hidden representation of the text phrase, wherein the encoder is trained during a first training phrase using self-supervised learning based on a first contrastive loss and during a second training phrase using supervised learning based on a second contrastive learning loss; identifying an intent of the text phrase from a predetermined set of intent labels using a classification network, wherein the classification network is jointly trained with the encoder in the second training phase; and generating a response to the text phrase based on the intent.

    Methods and systems for determining characteristics of a dialog between a computer and a user
    19.
    发明授权
    Methods and systems for determining characteristics of a dialog between a computer and a user 有权

    公开(公告)号：US11610584B2

    公开(公告)日：2023-03-21

    申请号：US16889669

    申请日：2020-06-01

    Applicant: Adobe Inc.

    Inventor： Tuan Manh Lai ,  Trung Bui ,  Quan Hung Tran

    IPC: G10L15/00 ,  G10L15/22 ,  G10L15/02 ,  G10L15/183 ,  G10L15/18

    Abstract: A computer-implemented method is disclosed for determining one or more characteristics of a dialog between a computer system and user. The method may comprise receiving a system utterance comprising one or more tokens defining one or more words generated by the computer system; receiving a user utterance comprising one or more tokens defining one or more words uttered by a user in response to the system utterance, the system utterance and the user utterance forming a dialog context; receiving one or more utterance candidates comprising one or more tokens; for each utterance candidate, generating an input sequence combining the one or more tokens of each of the system utterance, the user utterance, and the utterance candidate; and for each utterance candidate, evaluating the generated input sequence with a model to determine a probability that the utterance candidate is relevant to the dialog context.

    SEMANTIC IMAGE MANIPULATION USING VISUAL-SEMANTIC JOINT EMBEDDINGS
    20.
    发明申请
    SEMANTIC IMAGE MANIPULATION USING VISUAL-SEMANTIC JOINT EMBEDDINGS 有权

    公开(公告)号：US20220036127A1

    公开(公告)日：2022-02-03

    申请号：US16943511

    申请日：2020-07-30

    Applicant: Adobe Inc.

    Inventor： Zhe Lin ,  Xihui Liu ,  Quan Hung Tran ,  Jianming Zhang ,  Handong Zhao

    IPC: G06K9/62 ,  G06T11/00 ,  G06K9/46

    Abstract: The technology described herein is directed to a reinforcement learning based framework for training a natural media agent to learn a rendering policy without human supervision or labeled datasets. The reinforcement learning based framework feeds the natural media agent a training dataset to implicitly learn the rendering policy by exploring a canvas and minimizing a loss function. Once trained, the natural media agent can be applied to any reference image to generate a series (or sequence) of continuous-valued primitive graphic actions, e.g., sequence of painting strokes, that when rendered by a synthetic rendering environment on a canvas, reproduce an identical or transformed version of the reference image subject to limitations of an action space and the learned rendering policy.

Patent Agency Ranking