Domain-adaptive medical literature neural machine translation model training method
The invention discloses a method for training a neural machine translation model of field-adaptive medical literature. The method comprises the following steps: 1) performing data preprocessing on data sets inside and outside a field; 2) based on the out-of-domain sub-lexical training set, carrying...
Saved in:
Main Authors | , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
18.06.2021
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | The invention discloses a method for training a neural machine translation model of field-adaptive medical literature. The method comprises the following steps: 1) performing data preprocessing on data sets inside and outside a field; 2) based on the out-of-domain sub-lexical training set, carrying out dynamic decreasing training set training on an out-of-domain sub-lexical neural machine translation model; 3) using an improved data selection method to select a data set similar to the intra-domain parallel data set from the extra-domain data set to enhance the intra-domain data set; 4) training a small classifier or a language model based on the high-quality sub-lexical medical data set subjected to manual error correction to obtain training weights of sentence pairs of the sub-lexical training set in a domain, and adding the weights as training parameters into a continuous training process; and 5) in combination with the intra-domain sub-lexical training set and the training weight file obtained by processin |
---|---|
AbstractList | The invention discloses a method for training a neural machine translation model of field-adaptive medical literature. The method comprises the following steps: 1) performing data preprocessing on data sets inside and outside a field; 2) based on the out-of-domain sub-lexical training set, carrying out dynamic decreasing training set training on an out-of-domain sub-lexical neural machine translation model; 3) using an improved data selection method to select a data set similar to the intra-domain parallel data set from the extra-domain data set to enhance the intra-domain data set; 4) training a small classifier or a language model based on the high-quality sub-lexical medical data set subjected to manual error correction to obtain training weights of sentence pairs of the sub-lexical training set in a domain, and adding the weights as training parameters into a continuous training process; and 5) in combination with the intra-domain sub-lexical training set and the training weight file obtained by processin |
Author | DONG SHOUBIN ZHANG SHAOYUAN HU JINLONG YUAN HUA |
Author_xml | – fullname: DONG SHOUBIN – fullname: HU JINLONG – fullname: YUAN HUA – fullname: ZHANG SHAOYUAN |
BookMark | eNqNizsOwjAQBV1Awe8O5gApAhROiQKIigb6aBU_yEr2OnI2nJ8gcQCqkUYzSzOTJFiY-ylFYinIU6_8ho3w3FKwgRWZdMywgjFPJlLbscBqJhkCKSexMXmEr2FheU2zdsmvzfxJYcDmx5XZXs6P-lqgTw2GnloItKlvZbmrXOUO7rj_p_kA4BE6-A |
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 |
DocumentTitleAlternate | 一种领域适应医学文献神经机器翻译模型的训练方法 |
ExternalDocumentID | CN112989848A |
GroupedDBID | EVB |
ID | FETCH-epo_espacenet_CN112989848A3 |
IEDL.DBID | EVB |
IngestDate | Fri Jul 19 14:51:46 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | Chinese English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-epo_espacenet_CN112989848A3 |
Notes | Application Number: CN202110332815 |
OpenAccessLink | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20210618&DB=EPODOC&CC=CN&NR=112989848A |
ParticipantIDs | epo_espacenet_CN112989848A |
PublicationCentury | 2000 |
PublicationDate | 20210618 |
PublicationDateYYYYMMDD | 2021-06-18 |
PublicationDate_xml | – month: 06 year: 2021 text: 20210618 day: 18 |
PublicationDecade | 2020 |
PublicationYear | 2021 |
RelatedCompanies | SOUTH CHINA UNIVERSITY OF TECHNOLOGY |
RelatedCompanies_xml | – name: SOUTH CHINA UNIVERSITY OF TECHNOLOGY |
Score | 3.466022 |
Snippet | The invention discloses a method for training a neural machine translation model of field-adaptive medical literature. The method comprises the following... |
SourceID | epo |
SourceType | Open Access Repository |
SubjectTerms | CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
Title | Domain-adaptive medical literature neural machine translation model training method |
URI | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20210618&DB=EPODOC&locale=&CC=CN&NR=112989848A |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dS8MwED_m_HzTquj8IIL0LcjWj6UPRVzaMoR1Q6fsbaRdh4rtiq0I_vVe0m7zRV8vEJKjl7trfvn9AK6ZwM_CnDnUmDuCYv9lURHPBBV2J8KMEXXmSpJlENr9J_N-Yk0a8LZ8C6N4Qr8UOSJGVIzxXqrzOl__xPIUtrK4iV7RtLgNxq6n191xRzY4TPd6rj8aekOuc-7yUA8fXFlWMIeZ7G4DNmUZLXn2_eeefJWS_04pwT5sjXC2rDyAxveLBrt8qbymwc6gvvDWYFshNOMCjXUUFofw6C1SbOipmIlcnlYkrW5byPuKI5lInkq0pAormZBSpqQK9kaU-A1ZakOQSkP6CK4Cf8z7FNc5XTllysP1loxjaGaLLDkBEltdhyXCEsyRVOpt1o1tQ0RYiBjYqNjJKbT-nqf13-AZ7EkHS5hUm51Ds_z4TC4wIZfRpfLkD3EWkHs |
link.rule.ids | 230,309,786,891,25594,76903 |
linkProvider | European Patent Office |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1NT4NAEJ3U-lFvWjVav9bEcCOmUGA5EGOXEtRCG62mt2ahNGqkNIIx8dc7u6WtF70OyWaZMDv72LfvAVxSjp9Fa2yr-sTmKuIvQ-XxmKvc1CLsGJE2kZYsQWj6T627oTGswNviLozUCf2S4ohYUTHWeyHX69nqJ5YruZX5VfSKoezaGziuUqJjTQAcqrhtp9PvuT2mMOawUAkfHLGtoDZt0Zs1WLcQEkqo9NwWt1Jmv1uKtwMbfRxtWuxC5fulDjW2cF6rw1ZQHnjXYVMyNOMcg2UV5nvw6GYpAnqVj_lMrFYknZ-2kPelRjIROpUYSSVXMiGFaElz2huR5jdk4Q1B5h7S-3DhdQbMV3Geo2VSRixcvZJ-ANVpNk0OgcSGZdOEG5zaQkq9Sa3Y1HmEGxEdgYqZHEHj73Ea_z08h5o_CLqj7m14fwzbItmCMtWkJ1AtPj6TU2zORXQms_oDV--TZQ |
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=Domain-adaptive+medical+literature+neural+machine+translation+model+training+method&rft.inventor=DONG+SHOUBIN&rft.inventor=HU+JINLONG&rft.inventor=YUAN+HUA&rft.inventor=ZHANG+SHAOYUAN&rft.date=2021-06-18&rft.externalDBID=A&rft.externalDocID=CN112989848A |