公开(公告)号：US20230135163A1

公开(公告)日：2023-05-04

申请号：US17933821

申请日：2022-09-20

Applicant: Hyperconnect Inc.

Inventor： Jacob Richard Morton ,  Martin Kersner ,  Sang Il Ahn ,  Bu Ru Chang ,  Kwang Hee Choi

IPC: G06N3/08 ,  G06N3/04

Abstract: Provided is a method for training a model, including generating a plurality of attention maps by inputting training data into a previously trained teacher model, generating a set of attention weights of the teacher model based on the plurality of attention maps, generating a set of attention weights of a student model by inputting the training data into the student model, calculating a value of a first loss function based on the set of attention weights of the teacher model and the set of attention weights of the student model, calculating a value of a second loss function according to an inference of the student model with respect to the training data, and training the student model based on the value of the first loss function and the value of the second loss function.

公开(公告)号：US20230077528A1

公开(公告)日：2023-03-16

申请号：US17805191

申请日：2022-06-02

Applicant: Hyperconnect Inc.

Inventor： Enkhbayar Erdenee ,  Beom Su Kim ,  Seok Jun Seo ,  Sang Il Ahn ,  Bu Ru Chang ,  Seung Ju Han

IPC: G10L15/06 ,  G10L15/16

Abstract: A training method of a conversation model according to various example embodiments of the present disclosure may include identifying a first context, identifying a first response set corresponding to the first context based on a first model, identifying a response subset selected from the first response set based on a gold response corresponding to the first context and training a second model based on the first context information and the response subset.

公开(公告)号：US20230229864A1

公开(公告)日：2023-07-20

申请号：US18051429

申请日：2022-10-31

Applicant: Hyperconnect Inc.

Inventor： Beom Su Kim ,  Bu Ru Chang ,  Seung Ju Han

IPC: G06F40/35 ,  G06F40/56

CPC classification number: G06F40/35 ,  G06F40/56

Abstract: Provided is an apparatus for evaluating and improving responses, and a method and a computer readable recording medium thereof. The apparatus for evaluating responses according to the present disclosure obtains cluster classifying information for training responses, and based on distribution of clusters to which test responses output from the dialogue generation model are classified, evaluate semantic diversity of the responses output from the dialogue generation model.

公开(公告)号：US20230229964A1

公开(公告)日：2023-07-20

申请号：US18051430

申请日：2022-10-31

Applicant: Hyperconnect Inc.

Inventor： Beom Su Kim ,  Bu Ru Chang ,  Seung Ju Han

IPC: G06N20/00 ,  G06F40/35

CPC classification number: G06N20/00 ,  G06F40/35

Abstract: Provided is an apparatus for evaluating and improving responses, and a method and a computer readable recording medium thereof. The apparatus for evaluating responses according to the present disclosure obtains cluster classifying information for training responses, and based on distribution of clusters to which test responses output from the dialogue generation model are classified, evaluate semantic diversity of the responses output from the dialogue generation model.

公开(公告)号：US20230154453A1

公开(公告)日：2023-05-18

申请号：US18046455

申请日：2022-10-13

Applicant: Hyperconnect Inc.

Inventor： Enkhbayar Erdenee ,  Beom Su Kim ,  Sang Bum Kim ,  Seok Jun Seo ,  Jin Yong Yoo ,  Bu Ru Chang ,  Seung Ju Han

IPC: G10L15/02 ,  G06F40/20

CPC classification number: G10L15/02 ,  G06F40/20

Abstract: Systems and techniques to generate imitative responses are illustrated. response generation method performed in an electronic apparatus of the present disclosure includes acquiring at least one piece of utterance data, acquiring a first context corresponding to the utterance data from a context candidate set, generating one or more dialogue sets including the first context and the utterance data, receiving a second context from a user, and acquiring a response corresponding to the second context using a language model based on the one or more dialogue sets.

公开(公告)号：US20230080930A1

公开(公告)日：2023-03-16

申请号：US17807653

申请日：2022-06-17

Applicant: Hyperconnect Inc.

Inventor： Seok Jun Seo ,  Seung Ju Han ,  Beom Su Kim ,  Bu Ru Chang ,  Enkhbayar Erdenee

IPC: G06N5/02 ,  G06F40/35

Abstract: Disclosed is a method of training a dialogue model in an electronic device, the method including selecting a first context from a first dialogue data set including at least one pair of a context and a response corresponding to the context, generating a first response corresponding to the first context through a first dialogue model, generating an augmented dialogue dataset by incorporating a pair of the first context and the first response corresponding to the first context into the first dialogue data set, and training a second dialogue model based on the augmented dialogue dataset.

公开(公告)号：US20220207368A1

公开(公告)日：2022-06-30

申请号：US17646466

申请日：2021-12-29

Applicant: Hyperconnect, Inc.

Inventor： Sang Il Ahn ,  Joon Young Yi ,  Beom Su Kim ,  Bu Ru Chang

IPC: G06N3/08 ,  G06F5/01 ,  G06F17/16

Abstract: A method of training a neural network model for predicting a click-through rate (CTR) of a user in an electronic device includes normalizing an embedding vector on the basis of a feature-wise linear transformation parameter, and inputting the normalized embedding vector into a neural network layer, wherein the feature-wise linear transformation parameter is defined such that the same value is applied to all elements of the embedding vector.