知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

28 records (took 0.017 seconds)

    DETECTING OUT-OF-DOMAIN TEXT DATA IN DIALOG SYSTEMS USING ARTIFICIAL INTELLIGENCE
    11.
    发明公开
    DETECTING OUT-OF-DOMAIN TEXT DATA IN DIALOG SYSTEMS USING ARTIFICIAL INTELLIGENCE 审中-公开

    公开(公告)号：US20240070401A1

    公开(公告)日：2024-02-29

    申请号：US17897887

    申请日：2022-08-29

    Applicant: International Business Machines Corporation

    Inventor： Cheng Qian ,  Haode Qi ,  Saloni Potdar ,  Ladislav Kunc

    IPC: G06F40/40 ,  G06N5/02

    CPC classification number: G06F40/40 ,  G06N5/022

    Abstract: Methods, systems, and computer program products for detecting out-of-domain text data in dialog systems using artificial intelligence techniques are provided herein. A computer-implemented method includes updating artificial intelligence techniques related to out-of-domain text data detection, the updating based on encoding training data and generating regularized representations of at least a portion of the encoded training data by combining the at least a portion of the encoded training data and at least one intent centroid associated with the updated artificial intelligence techniques; encoding input text data; computing out-of-domain scores, in connection with the at least one dialog system, for at least a portion of the encoded input text data by processing the at least a portion of encoded input data using at least a portion of the one or more updated artificial intelligence techniques; and performing one or more automated actions based on the computed out-of-domain scores.

    OUT OF DOMAIN SENTENCE DETECTION
    12.
    发明公开
    OUT OF DOMAIN SENTENCE DETECTION 审中-公开

    公开(公告)号：US20240037331A1

    公开(公告)日：2024-02-01

    申请号：US17815630

    申请日：2022-07-28

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

    Inventor： Haode Qi ,  Cheng Qian ,  Ladislav Kunc ,  Saloni Potdar ,  Eric Donald Wayne

    IPC: G06F40/279 ,  G06F40/30 ,  G06F16/332

    CPC classification number: G06F40/279 ,  G06F40/30 ,  G06F16/3329

    Abstract: A method, a structure, and a computer system for OOD sentence detection in dialogue systems. The exemplary embodiments may include receiving, for a domain corresponding to a particular topic, one or more on-topic text inputs and one or more off-topic text inputs. The exemplary embodiments may further include encoding the one or more on-topic text inputs and the one or more off-topic text inputs into a latent space, as well as decoding the one or more on-topic text inputs and the one or more off-topic text inputs from the latent space. The exemplary embodiments may additionally include minimizing a reconstruction error between the encoded one or more on-topic text inputs and the decoded one or more on-topic text inputs, and maximizing a reconstruction error between the encoded one or more off-topic text inputs and the decoded one or more off-topic text inputs.

    Learning Parameter Sampling Configuration for Automated Machine Learning
    14.
    发明申请
    Learning Parameter Sampling Configuration for Automated Machine Learning 有权

    公开(公告)号：US20210304056A1

    公开(公告)日：2021-09-30

    申请号：US16829076

    申请日：2020-03-25

    Applicant: International Business Machines Corporation

    Inventor： Haode Qi ,  Ming Tan ,  Ladislav Kunc ,  Saloni Potdar

    IPC: G06N20/00 ,  G06N3/08 ,  G06K9/62

    Abstract: Mechanisms are provided for performing an automated machine learning (AutoML) operation to configure parameters of a machine learning model. AutoML logic is configured based on an initial parameter sampling configuration for sampling values of parameter(s) of the machine learning (ML) model. An initial AutoML process is executed on the ML model based on a dataset utilizing the initially configured AutoML logic, to generate at least one learned value for the parameter(s) of the ML model. The dataset is analyzed to extract a set of dataset characteristics that define properties of a format and/or a content of the dataset which are stored in association with the at least one learned value as part of a training dataset. A ML prediction model is trained based on the training dataset to predict, for new datasets, corresponding new sampling configuration information based on characteristics of the new datasets.

    System and method for enhanced chatflow application
    15.
    发明授权
    System and method for enhanced chatflow application 有权

    公开(公告)号：US11095590B2

    公开(公告)日：2021-08-17

    申请号：US15279248

    申请日：2016-09-28

    Applicant: International Business Machines Corporation

    Inventor： Raimo Bakis ,  Ladislav Kunc ,  David Nahamoo ,  Lazaros Polymenakos ,  John Zakos

    IPC: G06N20/00 ,  H04L12/58

    Abstract: Embodiments provide a computer implemented method, in a data processing system including a processor and a memory including instructions which are executed by the processor to cause the processor to train an enhanced chatflow system, the method including: ingesting a corpus of information including at least one user input node corresponding to a user question and at least one variation for each user input node; for each user input node: designating the node as a class; storing the node in a dialog node repository; designating each of the at least one variations as training examples for the designated class; converting the classes and the training examples into feature vector representations; training one or more training classifiers using the one or more feature vector representations of the classes; and training classification objectives using the one or more feature vector representations of the training examples.

    Routing text classifications within a cross-domain conversational service
    17.
    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.

    Cross-domain multi-task learning for text classification
    18.
    发明授权
    Cross-domain multi-task learning for text classification 有权

    公开(公告)号：US10937416B2

    公开(公告)日：2021-03-02

    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: G10L15/22 ,  G10L15/18 ,  G10L15/16 ,  G06N3/08 ,  G06F40/30

    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.

    WEIGHTING FEATURES FOR AN INTENT CLASSIFICATION SYSTEM
    19.
    发明申请
    WEIGHTING FEATURES FOR AN INTENT CLASSIFICATION SYSTEM 审中-公开

    公开(公告)号：US20200250270A1

    公开(公告)日：2020-08-06

    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: G06F17/27 ,  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.

Patent Agency Ranking