中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

53 records (took 0.08 seconds)

    Artificial intelligence based context dependent spellchecking
    21.
    发明授权
    Artificial intelligence based context dependent spellchecking 有权

    公开(公告)号：US11301626B2

    公开(公告)日：2022-04-12

    申请号：US16679464

    申请日：2019-11-11

    Applicant: International Business Machines Corporation

    Inventor： Panos Karagiannis ,  Ladislav Kune ,  Saloni Potdar ,  Haoyu Wang ,  Navneet N. Rao

    IPC: G06F40/232 ,  G06N20/00 ,  G06F40/30 ,  G06F40/284 ,  G06F40/211 ,  G06F40/253

    Abstract: Provided is a method, system, and computer program product for context-dependent spellchecking. The method comprises receiving context data to be used in spell checking. The method further comprises receiving a user input. The method further comprises identifying an out-of-vocabulary (OOV) word in the user input. An initial suggestion pool of candidate words is identified based, at least in part, on the context data. The method then comprises using a noisy channel approach to evaluate a probability that one or more of the candidate words of the initial suggestion pool is an intended word and should be used as a candidate for replacement of the OOV word. The method further comprises selecting one or more candidate words for replacement of the OOV word. The method further comprises outputting the one or more candidates.

    Unintended bias detection in conversational agent platforms with machine learning model
    22.
    发明授权
    Unintended bias detection in conversational agent platforms with machine learning model 有权

    公开(公告)号：US11270080B2

    公开(公告)日：2022-03-08

    申请号：US16743661

    申请日：2020-01-15

    Applicant: International Business Machines Corporation

    Inventor： Navneet N. Rao ,  Ming Tan ,  Haode Qi ,  Yang Yu ,  Panos Karagiannis ,  Saloni Potdar

    IPC: G06F40/247 ,  G06F40/279 ,  G06F40/30 ,  G06F40/289 ,  G06F40/216 ,  G06F16/9032

    Abstract: A mechanism is provided for implementing a bias detection mechanism that mitigates unintended bias in a conversational agent by leveraging conversational agent definitions, a conversational agent chat logs, and user satisfaction statistics. One or more protected attributes are identified within an utterance from the conversational agent chat logs. Using the identified protected attributes, a replacement utterance with a replacement term is generated for at least one of the identified protected attributes in the utterance. A score is generated for the utterance and the replacement utterance using utterance level relative term importance for protected attributes and regular terms in the utterance and the replacement utterance. Utilizing the scoring, a determination is made as to whether unintended bias exists within the utterance. Responsive to unintended bias being detected, an action is implemented that causes a change to a machine learning model used by the conversational agent.

    Weighting features for an intent classification system
    24.
    发明授权
    Weighting features for an intent classification system 有权

    公开(公告)号：US10977445B2

    公开(公告)日：2021-04-13

    申请号：US16265618

    申请日：2019-02-01

    Applicant: International Business Machines Corporation

    Inventor： Yang Yu ,  Ladislav Kunc ,  Haoyu Wang ,  Ming Tan ,  Saloni Potdar

    IPC: G10L15/22 ,  G06F40/30 ,  G06N20/00

    Abstract: A computer-implemented method includes obtaining a training data set including a plurality of training examples. The method includes generating, for each training example, multiple feature vectors corresponding, respectively, to multiple feature types. The method includes applying weighting factors to feature vectors corresponding to a subset of the feature types. The weighting factors are determined based on one or more of: a number of training examples, a number of classes associated with the training data set, an average number of training examples per class, a language of the training data set, a vocabulary size of the training data set, or a commonality of the vocabulary with a public corpus. The method includes concatenating the feature vectors of a particular training example to form an input vector and providing the input vector as training data to a machine-learning intent classification model to train the model to determine intent based on text input.

    CROSS-DOMAIN MULTI-TASK LEARNING FOR TEXT CLASSIFICATION
    25.
    发明申请
    CROSS-DOMAIN MULTI-TASK LEARNING FOR TEXT CLASSIFICATION 审中-公开

    公开(公告)号：US20200251100A1

    公开(公告)日：2020-08-06

    申请号：US16265740

    申请日：2019-02-01

    Applicant: International Business Machines Corporation

    Inventor： Ming Tan ,  Haoyu Wang ,  Ladislav Kunc ,  Yang Yu ,  Saloni Potdar

    IPC: G10L15/18 ,  G10L15/16 ,  G10L15/22 ,  G06F17/27 ,  G06N3/08

    Abstract: A method includes providing input text to a plurality of multi-task learning (MTL) models corresponding to a plurality of domains. Each MTL model is trained to generate an embedding vector based on the input text. The method further includes providing the input text to a domain identifier that is trained to generate a weight vector based on the input text. The weight vector indicates a classification weight for each domain of the plurality of domains. The method further includes scaling each embedding vector based on a corresponding classification weight of the weight vector to generate a plurality of scaled embedding vectors, generating a feature vector based on the plurality of scaled embedding vectors, and providing the feature vector to an intent classifier that is trained to generate, based on the feature vector, an intent classification result associated with the input text.

    Intent classification distribution calibration
    29.
    发明授权
    Intent classification distribution calibration 有权

    公开(公告)号：US11436528B2

    公开(公告)日：2022-09-06

    申请号：US16543117

    申请日：2019-08-16

    Applicant: International Business Machines Corporation

    Inventor： Haoyu Wang ,  Ming Tan ,  Dakuo Wang ,  Chuang Gan ,  Saloni Potdar

    IPC: G06N20/00 ,  G06N7/00 ,  G06F16/28

    Abstract: A method includes determining, based on an input data sample, a set of probabilities. Each probability of the set of probabilities is associated with a respective label of a set of labels. A particular probability associated with a particular label indicates an estimated likelihood that the input data sample is associated with the particular label. The method includes modifying the set of probabilities based on a set of adjustment factors to generate a modified set of probabilities. The set of adjustment factors is based on a first relative frequency distribution and a second relative frequency distribution. The first relative frequency distribution indicates for each label of the set of labels, a frequency of occurrence of the label among training data. The second relative frequency distribution indicates for each label of the set of labels, a frequency of occurrence of the label among post-training data provided to the trained classifier.

    Routing text classifications within a cross-domain conversational service
    30.
    发明授权
    Routing text classifications within a cross-domain conversational service 有权

    公开(公告)号：US11270077B2

    公开(公告)日：2022-03-08

    申请号：US16411076

    申请日：2019-05-13

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

    Inventor： Ming Tan ,  Ladislav Kunc ,  Yang Yu ,  Haoyu Wang ,  Saloni Potdar

    IPC: G06F40/30 ,  G06N20/00 ,  G10L15/18 ,  G10L15/22

    Abstract: A computing device receives a natural language input from a user. The computing device routes the natural language input from an active domain node of multiple domain nodes of a multi-domain context-based hierarchy to a leaf node of the domain nodes by selecting a parent domain node in the hierarchy until an off-topic classifier labels the natural language input as in-domain and then selecting a subdomain node in the hierarchy until an in-domain classifier labels the natural language input with a classification label, each of the plurality of domain nodes comprising a respective off-topic classifier and a respective in-domain classifier trained for a respective domain node. The computing device outputs the classification label determined by the leaf node.

Patent Agency Ranking