公开(公告)号：US20160210551A1

公开(公告)日：2016-07-21

申请号：US14992129

申请日：2016-01-11

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hodong LEE ,  Hoshik LEE ,  Heeyoul CHOI ,  Yunhong MIN ,  Sang Hyun YOO ,  Yeha LEE ,  Jihyun LEE ,  YoungSang CHOI

IPC: G06N3/08 ,  G10L15/16 ,  G06F17/27 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06F17/27 ,  G06N3/04 ,  G06N3/0445 ,  G06N3/084 ,  G10L15/005 ,  G10L15/16 ,  G10L15/19

Abstract: A method and apparatus for training a language model, include generating a first training feature vector sequence and a second training feature vector sequence from training data. The method is configured to perform forward estimation of a neural network based on the first training feature vector sequence, and perform backward estimation of the neural network based on the second training feature vector sequence. The method is further configured to train a language model based on a result of the forward estimation and a result of the backward estimation.

Abstract translation: 一种用于训练语言模型的方法和装置，包括从训练数据生成第一训练特征向量序列和第二训练特征向量序列。 该方法被配置为基于第一训练特征向量序列执行神经网络的前向估计，并且基于第二训练特征向量序列执行神经网络的向后估计。 该方法还被配置为基于正向估计的结果和后向估计的结果来训练语言模型。

公开(公告)号：US20190050395A1

公开(公告)日：2019-02-14

申请号：US15824743

申请日：2017-11-28

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Yunhong MIN

IPC: G06F17/27 ,  G06N3/08 ,  G06N3/04

CPC classification number: G06F17/2785 ,  G06N3/04 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/0481 ,  G06N3/088

Abstract: Methods and apparatuses for determining a domain of a sentence are disclosed. The apparatus may generate, using an autoencoder, an embedded feature from an input feature indicating an input sentence, and determine a domain of the input sentence based on a location of the embedded feature in an embedding space where embedded features are distributed.

公开(公告)号：US20180277098A1

公开(公告)日：2018-09-27

申请号：US15678390

申请日：2017-08-16

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Yunhong MIN

IPC: G10L15/06 ,  G06N3/08 ,  G10L25/30 ,  G10L15/02 ,  G10L15/16 ,  G10L15/14

CPC classification number: G10L15/063 ,  G06K9/6256 ,  G06K9/6262 ,  G06N3/08 ,  G06N3/084 ,  G10L15/02 ,  G10L15/14 ,  G10L15/16 ,  G10L25/30 ,  G10L2015/022 ,  G10L2015/0635

Abstract: A training method and apparatus for speech recognition is disclosed, where an example of the training method includes determining whether a current iteration for training a neural network is performed by an experience replay iteration using an experience replay set, selecting a sample from at least one of the experience replay set and a training set based on a result of the determining, and training the neural network based on the selected sample.