METHOD AND APPARATUS FOR TRAINING LANGUAGE MODEL, AND METHOD AND APPARATUS FOR RECOGNIZING LANGUAGE
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 se...
Saved in:
| Main Authors | , , , , , , , |
|---|---|
| Format | Patent |
| Language | English |
| Published |
21.07.2016
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| 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. |
|---|---|
| AbstractList | 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. |
| Author | LEE HODONG CHOI YOUNGSANG LEE HOSHIK LEE JIHYUN MIN YUNHONG LEE YEHA CHOI HEEYOUL YOO SANG HYUN |
| Author_xml | – fullname: CHOI HEEYOUL – fullname: YOO SANG HYUN – fullname: MIN YUNHONG – fullname: LEE HOSHIK – fullname: LEE YEHA – fullname: LEE JIHYUN – fullname: LEE HODONG – fullname: CHOI YOUNGSANG |
| BookMark | eNrjYmDJy89L5WRI9nUN8fB3UXD0A-KAAMcgx5DQYAU3_yCFkCBHTz9PP3cFH0c_91BHd1cFX38XVx8dsFKcuoJcnf3d_TyjkDXyMLCmJeYUp_JCaW4GZTfXEGcP3dSC_PjU4oLE5NS81JL40GAjA0MzI0MDU1NDR0Nj4lQBAAOkNnU |
| ContentType | Patent |
| DBID | EVB |
| DatabaseName | esp@cenet |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: EVB name: esp@cenet url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP sourceTypes: Open Access Repository |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine Chemistry Sciences Physics |
| ExternalDocumentID | US2016210551A1 |
| GroupedDBID | EVB |
| ID | FETCH-epo_espacenet_US2016210551A13 |
| IEDL.DBID | EVB |
| IngestDate | Fri Jul 19 14:47:05 EDT 2024 |
| IsOpenAccess | true |
| IsPeerReviewed | false |
| IsScholarly | false |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-epo_espacenet_US2016210551A13 |
| Notes | Application Number: US201614992129 |
| OpenAccessLink | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20160721&DB=EPODOC&CC=US&NR=2016210551A1 |
| ParticipantIDs | epo_espacenet_US2016210551A1 |
| PublicationCentury | 2000 |
| PublicationDate | 20160721 |
| PublicationDateYYYYMMDD | 2016-07-21 |
| PublicationDate_xml | – month: 07 year: 2016 text: 20160721 day: 21 |
| PublicationDecade | 2010 |
| PublicationYear | 2016 |
| RelatedCompanies | SAMSUNG ELECTRONICS CO., LTD |
| RelatedCompanies_xml | – name: SAMSUNG ELECTRONICS CO., LTD |
| Score | 3.0350752 |
| Snippet | A method and apparatus for training a language model, include generating a first training feature vector sequence and a second training feature vector sequence... |
| SourceID | epo |
| SourceType | Open Access Repository |
| SubjectTerms | ACOUSTICS CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING MUSICAL INSTRUMENTS PHYSICS SPEECH ANALYSIS OR SYNTHESIS SPEECH OR AUDIO CODING OR DECODING SPEECH OR VOICE PROCESSING SPEECH RECOGNITION |
| Title | METHOD AND APPARATUS FOR TRAINING LANGUAGE MODEL, AND METHOD AND APPARATUS FOR RECOGNIZING LANGUAGE |
| URI | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20160721&DB=EPODOC&locale=&CC=US&NR=2016210551A1 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dS8MwED_G_HzTqUydUlD6ZJE23VwehmRt1k3WtHStDF_GknUgSDdcxX_fJGy6F_eQh-RyITm4XH5J7g7gnvMp4hL4WFzab8udusLiyG5aDhbS-gmMuKO8kUPW6mfuy7g5rsDHxhdGxwn91sERpUYJqe-l3q-Xf5dYvv5buXrk77Jp8dxLO765RscqWppjm363Q-PIjzzT8zrZyGSJpjkqGaRNJFbaUwdpFWmfvnaVX8py26j0TmA_luMV5SlU8qIGR94m91oNDsP1k3cNDvQfTbGSjWs9XJ2BCGnaj3yDMFnimCQkzUaGBHRGmpABG7DAGBIWZCSgRhj5dPigu_7LlVAvCtjgbZvxHO56NPX6lpz35FdMk2y0vUh0AdViUeR1MGZ43p5J0Mxxc-rmGOE5EgoS4_aTQA5vXUJj10hXu8nXcKyq6r7TsRtQLT-_8htpqEt-q-X7A5VCjWQ |
| link.rule.ids | 230,309,786,891,25594,76906 |
| linkProvider | European Patent Office |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3NS8MwFH8Mv-ZNp-LH1ILSk0XadB89DMnarq22aelaGV7GknUgSDdcxX_fJGy6izvkkpeE5MHLyy957xeAe0oniHLgo1HuvzVzYjKNIr2lGRbj3o9ZiBoiGzkibT83n0etUQ0-1rkwkif0W5Ijcoti3N4ruV8v_i6xHBlbuXyk77xq_jTIeo66QseCLc3QVaffc5PYiW3Vtnv5UCWplBniM0gdc6y02xH8vOLw9NoXeSmLTacyOIK9hI9XVsdQK8oG1O3132sNOIhWT94N2JcxmmzJK1d2uDwBFrmZHzsKJrwkCU5xlg8VDuiULMUBCYinhJh4OfZcJYodN3yQTf_tlbp27JHgbbPjKdwN3Mz2NT7v8a-axvlwc5HoDHbKeVmcgzK1Zt0pB83Uak3MwkLWDDEBia1uhyGDti-guW2ky-3iW6j7WRSOw4C8XMGhEIm7T0Nvwk71-VVcc6dd0Rup6x9bbJBR |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=METHOD+AND+APPARATUS+FOR+TRAINING+LANGUAGE+MODEL%2C+AND+METHOD+AND+APPARATUS+FOR+RECOGNIZING+LANGUAGE&rft.inventor=CHOI+HEEYOUL&rft.inventor=YOO+SANG+HYUN&rft.inventor=MIN+YUNHONG&rft.inventor=LEE+HOSHIK&rft.inventor=LEE+YEHA&rft.inventor=LEE+JIHYUN&rft.inventor=LEE+HODONG&rft.inventor=CHOI+YOUNGSANG&rft.date=2016-07-21&rft.externalDBID=A1&rft.externalDocID=US2016210551A1 |