WO2018212584A3 - Method and apparatus for classifying class, to which sentence belongs, using deep neural network - Google Patents

Method and apparatus for classifying class, to which sentence belongs, using deep neural network Download PDF

Info

Publication number
WO2018212584A3
WO2018212584A3 PCT/KR2018/005598 KR2018005598W WO2018212584A3 WO 2018212584 A3 WO2018212584 A3 WO 2018212584A3 KR 2018005598 W KR2018005598 W KR 2018005598W WO 2018212584 A3 WO2018212584 A3 WO 2018212584A3
Authority
WO
WIPO (PCT)
Prior art keywords
neural network
deep neural
sentence
sentence belongs
learning
Prior art date
Application number
PCT/KR2018/005598
Other languages
French (fr)
Korean (ko)
Other versions
WO2018212584A2 (en
Inventor
송희준
쿨카르니니레시
Original Assignee
삼성전자 주식회사
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from KR1020180055651A external-priority patent/KR102071582B1/en
Application filed by 삼성전자 주식회사 filed Critical 삼성전자 주식회사
Priority to US16/613,317 priority Critical patent/US11568240B2/en
Publication of WO2018212584A2 publication Critical patent/WO2018212584A2/en
Publication of WO2018212584A3 publication Critical patent/WO2018212584A3/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/047—Probabilistic or stochastic networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Biophysics (AREA)
  • Evolutionary Computation (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Machine Translation (AREA)

Abstract

Provided are a method and an apparatus for classifying a class, to which a sentence belongs, using a deep neural network. One embodiment of the present disclosure provides a method and an apparatus for: learning a first sentence and a second sentence through a first neural network and a second neural network, respectively; acquiring a contrastive loss value on the basis of whether a first feature vector and a second feature vector, which are generated as output data of learning, are identical to classes to which the first and second sentences belong; and repeating learning so as to maximize the contrastive loss value.
PCT/KR2018/005598 2017-05-16 2018-05-16 Method and apparatus for classifying class, to which sentence belongs, using deep neural network WO2018212584A2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US16/613,317 US11568240B2 (en) 2017-05-16 2018-05-16 Method and apparatus for classifying class, to which sentence belongs, using deep neural network

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US201762506724P 2017-05-16 2017-05-16
US62/506,724 2017-05-16
KR10-2018-0055651 2018-05-15
KR1020180055651A KR102071582B1 (en) 2017-05-16 2018-05-15 Method and apparatus for classifying a class to which a sentence belongs by using deep neural network

Publications (2)

Publication Number Publication Date
WO2018212584A2 WO2018212584A2 (en) 2018-11-22
WO2018212584A3 true WO2018212584A3 (en) 2019-01-10

Family

ID=64274189

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2018/005598 WO2018212584A2 (en) 2017-05-16 2018-05-16 Method and apparatus for classifying class, to which sentence belongs, using deep neural network

Country Status (1)

Country Link
WO (1) WO2018212584A2 (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110210027B (en) * 2019-05-30 2023-01-24 杭州远传新业科技股份有限公司 Fine-grained emotion analysis method, device, equipment and medium based on ensemble learning
CN111259625B (en) * 2020-01-16 2023-06-27 平安科技（深圳）有限公司 Intention recognition method, device, equipment and computer readable storage medium
KR20210095431A (en) * 2020-01-23 2021-08-02 삼성전자주식회사 Electronic device and control method thereof
CN111310823B (en) * 2020-02-12 2024-03-29 北京迈格威科技有限公司 Target classification method, device and electronic system

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140025382A1 (en) * 2012-07-18 2014-01-23 Kabushiki Kaisha Toshiba Speech processing system
WO2016039751A1 (en) * 2014-09-11 2016-03-17 Nuance Communications, Inc. Method for scoring in an automatic speech recognition system
US20160092766A1 (en) * 2014-09-30 2016-03-31 Google Inc. Low-rank hidden input layer for speech recognition neural network
KR20160069329A (en) * 2014-12-08 2016-06-16 삼성전자주식회사 Method and apparatus for training language model, method and apparatus for recognizing speech
KR20170011636A (en) * 2015-07-23 2017-02-02 삼성전자주식회사 Speech recognition apparatus and method, Model generation apparatus and method for Speech recognition apparatus

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140025382A1 (en) * 2012-07-18 2014-01-23 Kabushiki Kaisha Toshiba Speech processing system
WO2016039751A1 (en) * 2014-09-11 2016-03-17 Nuance Communications, Inc. Method for scoring in an automatic speech recognition system
US20160092766A1 (en) * 2014-09-30 2016-03-31 Google Inc. Low-rank hidden input layer for speech recognition neural network
KR20160069329A (en) * 2014-12-08 2016-06-16 삼성전자주식회사 Method and apparatus for training language model, method and apparatus for recognizing speech
KR20170011636A (en) * 2015-07-23 2017-02-02 삼성전자주식회사 Speech recognition apparatus and method, Model generation apparatus and method for Speech recognition apparatus

Also Published As

Publication number Publication date
WO2018212584A2 (en) 2018-11-22

Similar Documents

Publication Publication Date Title
WO2017052709A3 (en) Transfer learning in neural networks
WO2018212584A3 (en) Method and apparatus for classifying class, to which sentence belongs, using deep neural network
WO2018149898A3 (en) Methods and systems for network self-optimization using deep learning
MX2017008583A (en) Discriminating ambiguous expressions to enhance user experience.
EP3806089A4 (en) Mixed speech recognition method and apparatus, and computer readable storage medium
EP3742346A3 (en) Method for training generative adversarial network (gan), method for generating images by using gan, and computer readable storage medium
WO2020132102A3 (en) Neural networks for coarse- and fine-object classifications
WO2018203147A3 (en) Multi-lingual semantic parser based on transferred learning
SG11201906576WA (en) Speech wakeup method, apparatus, and electronic device
EP4255086A3 (en) Collision avoidance adaptation for autonomous transmission systems
WO2016004266A3 (en) Generating computer responses to social conversational inputs
EP2953065A3 (en) Generating representations of input sequences using neural networks
EP3657428A4 (en) Data learning server, and method for generating and using learning model thereof
EP3021185A3 (en) Process control system and configuration system
MX346334B (en) Method and system for automatic speech recognition.
BR112017006053A2 (en) communication method and apparatus
WO2016164680A3 (en) Automated model development process
MX2016013015A (en) Methods and systems of handling a dialog with a robot.
MX362590B (en) Methods and systems for generation of flexible sentences in a social networking system.
GB2545070A (en) Generating molecular encoding information for data storage
GB2571645A (en) Automatic classification of drilling reports with deep natural language processing
GB2571841A (en) Automated mutual improvement of oilfield models
EP3371750A4 (en) System and method for rule generation using data processed by binary classifier
WO2014070306A3 (en) System and method for applying a business rule management system to a customer relationship management system
EP3936224A4 (en) Data generation device, data generation method, learning device, and learning method

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18802102

Country of ref document: EP

Kind code of ref document: A2

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18802102

Country of ref document: EP

Kind code of ref document: A2