基于神经耦合模型的异构词法数据转化和融合

为了扩大人工标注数据的规模,从而提高模型性能,尝试充分利用已有的异构人工标注数据训练模型参数.将Li等2015年提出的耦合序列标注方法扩展到基于BiLSTM的深度学习框架,直接在两个异构训练数据上训练参数,测试阶段则同时预测两个标签序列.在词性标注、分词词性联合标注两个任务上进行大量实验,结果表明,与多任务学习方法和传统耦合模型相比,神经耦合模型在利用词法异构数据方面更优越,在异构数据转化和融合两个场景上都取得更高的性能....

Full description

Saved in:
Bibliographic Details
Published in北京大学学报（自然科学版） Vol. 56; no. 1; pp. 97 - 104
Main Authors 黄德朋, 李正华, 龚晨, 张民
Format Journal Article
LanguageChinese
Published 苏州大学计算机科学与技术学院,苏州,215006 20.01.2020
Subjects
词性标注
BiLSTM
耦合模型
分词
深度学习
Online AccessGet full text
ISSN0479-8023
DOI10.13209/j.0479-8023.2019.098

Cover

Abstract 为了扩大人工标注数据的规模,从而提高模型性能,尝试充分利用已有的异构人工标注数据训练模型参数.将Li等2015年提出的耦合序列标注方法扩展到基于BiLSTM的深度学习框架,直接在两个异构训练数据上训练参数,测试阶段则同时预测两个标签序列.在词性标注、分词词性联合标注两个任务上进行大量实验,结果表明,与多任务学习方法和传统耦合模型相比,神经耦合模型在利用词法异构数据方面更优越,在异构数据转化和融合两个场景上都取得更高的性能.
AbstractList 为了扩大人工标注数据的规模,从而提高模型性能,尝试充分利用已有的异构人工标注数据训练模型参数.将Li等2015年提出的耦合序列标注方法扩展到基于BiLSTM的深度学习框架,直接在两个异构训练数据上训练参数,测试阶段则同时预测两个标签序列.在词性标注、分词词性联合标注两个任务上进行大量实验,结果表明,与多任务学习方法和传统耦合模型相比,神经耦合模型在利用词法异构数据方面更优越,在异构数据转化和融合两个场景上都取得更高的性能.
Author 李正华
张民
龚晨
黄德朋
AuthorAffiliation 苏州大学计算机科学与技术学院,苏州,215006
AuthorAffiliation_xml – name: 苏州大学计算机科学与技术学院,苏州,215006
Author_FL LI Zhenghua
ZHANG Min
GONG Chen
HUANG Depeng
Author_FL_xml – sequence: 1
  fullname: HUANG Depeng
– sequence: 2
  fullname: LI Zhenghua
– sequence: 3
  fullname: GONG Chen
– sequence: 4
  fullname: ZHANG Min
Author_xml – sequence: 1
  fullname: 黄德朋
– sequence: 2
  fullname: 李正华
– sequence: 3
  fullname: 龚晨
– sequence: 4
  fullname: 张民
BookMark eNo9jT9Lw0AYh2-oYK39CM5Oie-9uUvuwEWK_6DgonO5y_XEICkYxI4iHQRbLUIdHCIOioOo4Fb123hJPoYFxekHDw_Pb4HU0l7aJWSJgk8DBLmS-MAi6QnAwEeg0gcpaqT-D-dJM8sONFBEIUNG62TV3U2_p5flQ15-XFWnj258Xjzdu_yivB24z7MiH1Svo-J9UkzeitFL9fXshjfueljlo5m5SOasOsy6zb9tkL2N9d3Wltfe2dxurbW9jAIyLxKCmYiHlkoLseBaxxihNBgjMBVyozTnyjAIY2pjNGAtsihANEJwHtKgQZZ_uycqtSrd7yS946N09tjRien3NQICUKAs-AEB7WAi
ContentType Journal Article
Copyright Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
Copyright_xml – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
DBID 2B.
4A8
92I
93N
PSX
TCJ
DOI 10.13209/j.0479-8023.2019.098
DatabaseName Wanfang Data Journals - Hong Kong
WANFANG Data Centre
Wanfang Data Journals
万方数据期刊 - 香港版
China Online Journals (COJ)
China Online Journals (COJ)
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Sciences (General)
DocumentTitle_FL Neural Network Coupled Model for Conversion and Exploitation of Heterogeneous Lexical Annotations
EndPage 104
ExternalDocumentID bjdxxb202001014
GrantInformation_xml – fundername: 国家自然科学基金; 江苏高校优势学科建设工程项目资助
  funderid: (61525205,61876116,61702518); 江苏高校优势学科建设工程项目资助
GroupedDBID -01
23M
2B.
4A8
5GY
8FE
8FH
92E
92I
93N
AAABJ
AAQEF
ABJNI
ABLSY
ABPYQ
ABUWG
ABVRV
ACECN
ACGFS
ACPRK
ACTRF
ADCJG
ADGMY
ADMLS
ADMQQ
ADRFT
ADZSZ
AENOO
AEXCR
AFKRA
AFSCH
AFTSM
AFZMG
AHIBC
AIVZI
AJZVN
ALMA_UNASSIGNED_HOLDINGS
BBNVY
BENPR
BHPHI
BPHCQ
BVBZV
CCEZO
CCPQU
CCVFK
CW9
HCIFZ
LK8
M7P
P2P
PDI
PHGZM
PHGZT
PMFND
PQQKQ
PSX
TCJ
TGP
U1G
U5K
UY8
ID FETCH-LOGICAL-s1024-7884d756f19f0c85bbc2729d2c204a65dab55ad406c1fc2d0ff247322d8855613
ISSN 0479-8023
IngestDate Thu May 29 04:00:37 EDT 2025
IsPeerReviewed false
IsScholarly true
Issue 1
Keywords 词性标注
BiLSTM
耦合模型
分词
深度学习
Language Chinese
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-s1024-7884d756f19f0c85bbc2729d2c204a65dab55ad406c1fc2d0ff247322d8855613
PageCount 8
ParticipantIDs wanfang_journals_bjdxxb202001014
PublicationCentury 2000
PublicationDate 2020-01-20
PublicationDateYYYYMMDD 2020-01-20
PublicationDate_xml – month: 01
  year: 2020
  text: 2020-01-20
  day: 20
PublicationDecade 2020
PublicationTitle 北京大学学报（自然科学版）
PublicationTitle_FL Acta Scientiarum Naturalium Universitatis Pekinensis
PublicationYear 2020
Publisher 苏州大学计算机科学与技术学院,苏州,215006
Publisher_xml – name: 苏州大学计算机科学与技术学院,苏州,215006
SSID ssib012289641
ssib051370299
ssj0030172
ssib001522812
ssib002258124
ssib000862120
ssib030194702
ssib008143590
ssib002040163
ssib006703675
ssib038076459
Score 2.257665
Snippet 为了扩大人工标注数据的规模,从而提高模型性能,尝试充分利用已有的异构人工标注数据训练模型参数.将Li等2015年提出的耦合序列标注方法扩展到基于BiLSTM的深度学习框架,直...
SourceID wanfang
SourceType Aggregation Database
StartPage 97
Title 基于神经耦合模型的异构词法数据转化和融合
URI https://d.wanfangdata.com.cn/periodical/bjdxxb202001014
Volume 56
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVPQU
  databaseName: East & South Asia Database
  issn: 0479-8023
  databaseCode: BVBZV
  dateStart: 20170101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://search.proquest.com/eastsouthasia
  omitProxy: false
  ssIdentifier: ssj0030172
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  issn: 0479-8023
  databaseCode: BENPR
  dateStart: 20170101
  customDbUrl: http://www.proquest.com/pqcentral?accountid=15518
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.proquest.com/central
  omitProxy: true
  ssIdentifier: ssj0030172
  providerName: ProQuest
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LaxRBEB7yuHgR4wPf7MEGPUyc6Znu6QYvPbu9BMEgkkBuYR47Sg4bMAmEnERyEExUhHjwsOJB8SAqeIv6I_wP7mZ_hlU9vbuTZMHHZWiqq3uqvtqZqprtrnaca8L30iJizBV5wNwwSZmbJrnnCh4lklMvysxemDvzfG4xvL3EliYmf1ZWLW2sp7PZ1th9Jf9jVaCBXXGX7D9YdjgpEKAN9oUrWBiuf2VjohmRTRIrokO8Ck10RBQQTSOOiWgSLXA1g-KG2SNCEM2JEkT5hqKJiJFZwvAQKXGdCIo82BXicNUkooGUOCCSmS5g87ABdKWRJ4ZGHYeLOpHlvSi2oQvnaQzvXo2GB_yRlb-cQYVERabRsGLbBtxOoXa6aYQURjXQV6H8IGrMjfqgi18ZBV3SMJejhh8-iJYGoVJpTeLIaAYs8YgFCA0DKzfTBUZipByaRSN6yCsB2FGPwVIZnACt8riwwRcWigv1XOoNnwmjTGkwhrKgCY9jIRButFyEDTkQOVbjNAdEhBUegBOeZVbNCo80QlN40sYIQOsQqnker3iLMJIuVvOrujbGjz3CpZ8q10TbiMceAH3MmQbUFKNdmR3OjUsh5axXnht-pE55upJvbqaInzn_edKZpuBovSlnOtbzd-8dyqF9Wo3ZKT1UAw_cis-rMSbDIHTkJLBkXCXmFRjxj_7q9WE2yUcxPjgwGUajGnd4wEK1gBLzA-jFnLwM3wL8KILh20Bnu-0Pwbg5Dgqz269dJO37lcB04ZRz0maUNVW-Hmacia0Hp50Z67PXatdtYfkbZ5xb3Tf7v_afHbzrHHx73n_0vvviSe_D227n6cHr7e73x73Odv_zbu_rXm_vS2_3U__Hx-7Oq-7LnX5nFzjPOotNvVCfc-3pKe4aJA0hLhMO84jxwpeFlwmWphmFTDqnGSCccJbDe5klOQT0mV9kNPeKgoYR-PdcCDwzNzjnTLVX263zTo1mCYdEIodULQhbGZVF0Yo4h-QsLbCE5wWnZiFYtm_HteUjP4eLf2a55JwYPX2Xnan1hxutKxDxr6dX7W_oN3lXuFc
linkProvider ProQuest
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%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8E%E7%A5%9E%E7%BB%8F%E8%80%A6%E5%90%88%E6%A8%A1%E5%9E%8B%E7%9A%84%E5%BC%82%E6%9E%84%E8%AF%8D%E6%B3%95%E6%95%B0%E6%8D%AE%E8%BD%AC%E5%8C%96%E5%92%8C%E8%9E%8D%E5%90%88&rft.jtitle=%E5%8C%97%E4%BA%AC%E5%A4%A7%E5%AD%A6%E5%AD%A6%E6%8A%A5%EF%BC%88%E8%87%AA%E7%84%B6%E7%A7%91%E5%AD%A6%E7%89%88%EF%BC%89&rft.au=%E9%BB%84%E5%BE%B7%E6%9C%8B&rft.au=%E6%9D%8E%E6%AD%A3%E5%8D%8E&rft.au=%E9%BE%9A%E6%99%A8&rft.au=%E5%BC%A0%E6%B0%91&rft.date=2020-01-20&rft.pub=%E8%8B%8F%E5%B7%9E%E5%A4%A7%E5%AD%A6%E8%AE%A1%E7%AE%97%E6%9C%BA%E7%A7%91%E5%AD%A6%E4%B8%8E%E6%8A%80%E6%9C%AF%E5%AD%A6%E9%99%A2%2C%E8%8B%8F%E5%B7%9E%2C215006&rft.issn=0479-8023&rft.volume=56&rft.issue=1&rft.spage=97&rft.epage=104&rft_id=info:doi/10.13209%2Fj.0479-8023.2019.098&rft.externalDocID=bjdxxb202001014
thumbnail_s http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fbjdxxb%2Fbjdxxb.jpg