Joint Entity and Event Extraction with Generative Adversarial Imitation Learning

We propose a new framework for entity and event extraction based on generative adversarial imitation learning—an inverse reinforcement learning method using a generative adversarial network (GAN). We assume that instances and labels yield to various extents of difficulty and the gains and penalties...

Full description

Saved in:
Bibliographic Details
Published inData intelligence Vol. 1; no. 2; pp. 99 - 120
Main Authors Zhang, Tongtao, Ji, Heng, Sil, Avirup
Format Journal Article
LanguageEnglish
Published One Rogers Street, Cambridge, MA 02142-1209, USA MIT Press 01.04.2019
MIT Press Journals, The
Subjects
Online AccessGet full text

Cover

Loading…
Abstract We propose a new framework for entity and event extraction based on generative adversarial imitation learning—an inverse reinforcement learning method using a generative adversarial network (GAN). We assume that instances and labels yield to various extents of difficulty and the gains and penalties (rewards) are expected to be diverse. We utilize discriminators to estimate proper rewards according to the difference between the labels committed by the ground-truth (expert) and the extractor (agent). Our experiments demonstrate that the proposed framework outperforms state-of-the-art methods.
AbstractList We propose a new framework for entity and event extraction based on generative adversarial imitation learning—an inverse reinforcement learning method using a generative adversarial network (GAN). We assume that instances and labels yield to various extents of difficulty and the gains and penalties (rewards) are expected to be diverse. We utilize discriminators to estimate proper rewards according to the difference between the labels committed by the ground-truth (expert) and the extractor (agent). Our experiments demonstrate that the proposed framework outperforms state-of-the-art methods.
Author Sil, Avirup
Ji, Heng
Zhang, Tongtao
Author_xml – sequence: 1
  givenname: Tongtao
  surname: Zhang
  fullname: Zhang, Tongtao
  organization: Computer Science Department, Rensselaer Polytechnic Institute, Troy, New York 12180-3590, USA
– sequence: 2
  givenname: Heng
  orcidid: 0000-0002-7954-7994
  surname: Ji
  fullname: Ji, Heng
  email: jih@rpi.edu
  organization: Computer Science Department, Rensselaer Polytechnic Institute, Troy, New York 12180-3590, USA
– sequence: 3
  givenname: Avirup
  surname: Sil
  fullname: Sil, Avirup
  organization: IBM Research Al, Armonk, New York 10504-1722, USA
BookMark eNp1kM1OAjEURhuDiYjsfIBJ3LhwtP8zXRlCEDEkutDEXVM6HS2BDnbKKD69RUgkBFdtmvN99_acgparnAHgHMFrhDi-KawLUkkIIaJHoI05RSkl7LW1cz8B3bqeRgQjjgRlbfD0UMVcMnDBhlWiXJEMGrN--Ape6WArl3za8J4MjTNeBduYpFc0xtfKWzVLRnMb1C81Nso7697OwHGpZrXpbs8OeLkbPPfv0_HjcNTvjVNNBAxpxgXXpiAFVTlDuZkUWKAM6UzgosRGFyXPWM44IYiQbJIJpjimJUMToUlJFemAi03vwlcfS1MHOa2W3sWREucCCp5hlkfqakNpX9W1N6VceDtXfiURlGttcldbxPEerrf_izbs7L_Q7SYUXfwtsUYaZLEkkFDEJI7OY1hCIb_tYr_h8kDDwWE_zP-Vzw
CitedBy_id crossref_primary_10_1007_s00521_020_05360_1
crossref_primary_10_1109_ACCESS_2020_2965964
crossref_primary_10_1016_j_jbi_2023_104371
crossref_primary_10_1016_j_artint_2024_104144
crossref_primary_10_1109_TASLP_2021_3138670
crossref_primary_10_1016_j_knosys_2024_112041
crossref_primary_10_1145_3464426
crossref_primary_10_1007_s11280_023_01216_5
crossref_primary_10_3390_electronics13101807
crossref_primary_10_1109_TKDE_2023_3266495
crossref_primary_10_1109_TNNLS_2022_3213168
crossref_primary_10_1016_j_procs_2020_06_066
crossref_primary_10_1016_j_ipm_2021_102596
crossref_primary_10_3390_app13169257
crossref_primary_10_1016_j_asej_2024_103040
crossref_primary_10_1016_j_neucom_2022_01_069
crossref_primary_10_3390_electronics12061386
crossref_primary_10_1016_j_eswa_2022_118257
crossref_primary_10_1109_ACCESS_2019_2956831
crossref_primary_10_1109_ACCESS_2020_2985126
crossref_primary_10_1109_TBDATA_2023_3291563
crossref_primary_10_1109_ACCESS_2020_3024872
crossref_primary_10_3390_app14072902
crossref_primary_10_1049_cit2_12062
crossref_primary_10_1007_s13042_022_01760_y
crossref_primary_10_1162_coli_a_00415
crossref_primary_10_1371_journal_pone_0272353
crossref_primary_10_3389_fphy_2022_1044919
crossref_primary_10_1109_ACCESS_2021_3130956
crossref_primary_10_7717_peerj_cs_1066
crossref_primary_10_1016_j_ipm_2021_102636
crossref_primary_10_1088_1742_6596_2171_1_012062
crossref_primary_10_1155_2021_5599962
Cites_doi 10.1162/neco.1997.9.8.1735
10.1007/s10994-009-5106-x
ContentType Journal Article
Copyright 2019. This work is published under https://creativecommons.org/licenses/by/4.0/legalcode (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: 2019. This work is published under https://creativecommons.org/licenses/by/4.0/legalcode (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID AAYXX
CITATION
8FE
8FG
ABJCF
ABUWG
AFKRA
ARAPS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
GNUQQ
HCIFZ
JQ2
K7-
L6V
M7S
P62
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PTHSS
DOI 10.1162/dint_a_00014
DatabaseName CrossRef
ProQuest SciTech Collection
ProQuest Technology Collection
Materials Science & Engineering Collection
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
Proquest Central Journals
Technology Collection
ProQuest One Community College
ProQuest Central
ProQuest Central Student
Proquest SciTech Premium Collection
ProQuest Computer Science Collection
Computer Science Database
ProQuest Engineering Collection
Engineering Database
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Premium
ProQuest One Academic
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic
ProQuest One Academic UKI Edition
Engineering Collection
DatabaseTitle CrossRef
Publicly Available Content Database
Computer Science Database
ProQuest Central Student
Technology Collection
ProQuest One Academic Middle East (New)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Computer Science Collection
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest Engineering Collection
ProQuest Central Korea
ProQuest Central (New)
Engineering Collection
Advanced Technologies & Aerospace Collection
Engineering Database
ProQuest One Academic Eastern Edition
ProQuest Technology Collection
ProQuest SciTech Collection
ProQuest One Academic UKI Edition
Materials Science & Engineering Collection
ProQuest One Academic
ProQuest One Academic (New)
DatabaseTitleList CrossRef
Publicly Available Content Database

Database_xml – sequence: 1
  dbid: 8FG
  name: ProQuest Technology Collection
  url: https://search.proquest.com/technologycollection1
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
EISSN 2641-435X
EndPage 120
ExternalDocumentID 10_1162_dint_a_00014
dint_a_00014.pdf
GroupedDBID ABJCF
AFKRA
ALMA_UNASSIGNED_HOLDINGS
ARAPS
BENPR
BGLVJ
CCPQU
EBS
EJD
GROUPED_DOAJ
HCIFZ
JMNJE
K7-
LM3
M7S
OK1
PIMPY
PTHSS
RMI
AAYXX
CITATION
PHGZM
PHGZT
PQGLB
8FE
8FG
ABUWG
AZQEC
DWQXO
GNUQQ
JQ2
L6V
P62
PKEHL
PQEST
PQQKQ
PQUKI
ID FETCH-LOGICAL-c390t-7696ced3d4a8518ebd29171c792df2ecdf675856331337b795a624f51b9c3f4a3
IEDL.DBID BENPR
ISSN 2641-435X
IngestDate Fri Jul 25 11:51:33 EDT 2025
Thu Apr 24 23:02:25 EDT 2025
Tue Aug 05 12:05:25 EDT 2025
Thu Mar 28 07:29:35 EDT 2024
Tue Mar 01 17:18:16 EST 2022
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c390t-7696ced3d4a8518ebd29171c792df2ecdf675856331337b795a624f51b9c3f4a3
Notes Spring, 2019
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-7954-7994
OpenAccessLink https://www.proquest.com/docview/2890967258?pq-origsite=%requestingapplication%
PQID 2890967258
PQPubID 6535869
PageCount 22
ParticipantIDs mit_journals_dintv1i2_303415_2021_11_09_zip_dint_a_00014
mit_journals_10_1162_dint_a_00014
crossref_citationtrail_10_1162_dint_a_00014
crossref_primary_10_1162_dint_a_00014
proquest_journals_2890967258
PublicationCentury 2000
PublicationDate 2019-04-01
PublicationDateYYYYMMDD 2019-04-01
PublicationDate_xml – month: 04
  year: 2019
  text: 2019-04-01
  day: 01
PublicationDecade 2010
PublicationPlace One Rogers Street, Cambridge, MA 02142-1209, USA
PublicationPlace_xml – name: One Rogers Street, Cambridge, MA 02142-1209, USA
– name: Cambridge
PublicationTitle Data intelligence
PublicationYear 2019
Publisher MIT Press
MIT Press Journals, The
Publisher_xml – name: MIT Press
– name: MIT Press Journals, The
References ref23
Sutton R.S. (ref36) 2000
Walker C. (ref1) 2006
ref33
References_xml – ident: ref33
  doi: 10.1162/neco.1997.9.8.1735
– volume-title: ACE 2005 multilingual training corpus
  year: 2006
  ident: ref1
– ident: ref23
  doi: 10.1007/s10994-009-5106-x
– start-page: 1057
  volume-title: Advances in Neural Information Processing Systems 12 (NIPS 1999)
  year: 2000
  ident: ref36
SSID ssj0002161945
Score 2.4514334
Snippet We propose a new framework for entity and event extraction based on generative adversarial imitation learning—an inverse reinforcement learning method using a...
SourceID proquest
crossref
mit
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 99
SubjectTerms Blasphemy
Event extraction
Generative adversarial network
Generative adversarial networks
Imitation learning
Information extraction
Labels
Title Joint Entity and Event Extraction with Generative Adversarial Imitation Learning
URI https://direct.mit.edu/dint/article/doi/10.1162/dint_a_00014
https://www.proquest.com/docview/2890967258
Volume 1
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LSwMxEA62vXgRRcU3EfQki202rzmJytbHoRSx4C1ks7tS0LbaVdRf72Q39YneFjJZdpPJzDePzBCyZ0WhUy1FZJ2FiIt2HCFqhQgAHy1Iy-sE2Z48H_DLG3ETHG7TkFY5k4mVoM7GzvvID31ADKRiQh9NHiLfNcpHV0MLjQZpoQjWuklaJ0mvf_XhZWEdb6WLWca7ZIeoEUpjq5gr_6aLGvfD8pdArrRMd5EsBHhIj-v9XCJz-WiZ9C_H-Dqa-Bu1rxRNf5r4LEWavJSP9b0E6t2ptC4h7eUXrfosT63nLnpxH-pw01BM9XaFDLrJ9el5FDohRC6GdhkpCdLlWZxxiwhJ52nG0MzqOAUsK1jusqLC_TKO0eRUqQJhJeOF6KTg4oLbeJU0R-NRvkYoaOYyBbIQecaVkmnBEONxW4CT4JRcJwezNTEufJ7vVnFnKnNBMvN1BdfJ_gf1pC6P8QfdLv6rCedj-geN_kbjx547Q2ZQyyLMMAx3E2eZNpi34eTH1K3Zvn3O_-SYjf-HN8k8wiCo83G2SLN8fMq3EWqU6Q5p6O7ZTuCqd13D1Kk
linkProvider ProQuest
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3JTsMwELVoOcAFgQBRViPBCUW0jpf4gBCClpZNHEDiZhw7QZWgLW1YykfxjYyzlE1w6y2Sx1ZiT2bejGdBaEuzOAgDzjxttPQoq_oeoFbpSQmPWnJNswDZC968pic37GYCvRe5MC6sspCJqaC2XeN85LvuQkxyQViw33v0XNcod7tatNDI2OI0Gr6AyTbYax3B-W4T0qhfHTa9vKuAZ8C-TzzBJTeR9S3VgDaCKLQETJaaEZLYmETGximG5r4P5psIhWSaExqzWiiNH1Ptw7olNEl90OQuM71xPPLpkJrzCbAivp6TXdA_idLpDS_9pvlKD-3kl_hPdVpjFs3kYBQfZNwzhyaizjy6POnCcrju8neHWHcsrruYSFx_TfpZFgR2zlucFax20hKnXZ0H2vEybj3kVb9xXrr1bgFdj2WHFlG50-1ESwjLgBgrJI9ZZKkQPIwJIEqqY2m4NIJX0E6xJ8rkr-d6Y9yr1DjhRH3dwQraHlH3smIcf9Btwreq_G8c_EETfKNxY8-1NlGg0wHUKAKnCbNUVaq3du_H1NXi3D7nf_Ln8v_DG2iqeXV-ps5aF6craBoAmMwigVZROek_RWsAcpJwPeUsjG7HzcofZd8OkA
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=Joint+Entity+and+Event+Extraction+with+Generative+Adversarial+Imitation+Learning&rft.jtitle=Data+intelligence&rft.au=Zhang%2C+Tongtao&rft.au=Ji%2C+Heng&rft.au=Sil%2C+Avirup&rft.date=2019-04-01&rft.pub=MIT+Press+Journals%2C+The&rft.eissn=2641-435X&rft.volume=1&rft.issue=2&rft.spage=99&rft_id=info:doi/10.1162%2Fdint_a_00014
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2641-435X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2641-435X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2641-435X&client=summon