Publication:
PROTEST-ER: retraining BERT for protest event extraction

Simple item page
dc.contributor.coauthorCaselli, Tommaso
dc.contributor.coauthorBasile, Angelo
dc.contributor.departmentN/A
dc.contributor.departmentDepartment of Sociology
dc.contributor.kuauthorMutlu, Osman
dc.contributor.kuauthorHürriyetoğlu, Ali
dc.contributor.kuprofilePhD Student
dc.contributor.kuprofileTeaching Faculty
dc.contributor.otherDepartment of Sociology
dc.contributor.schoolcollegeinstituteGraduate School of Sciences and Engineering
dc.contributor.schoolcollegeinstituteCollege of Social Sciences and Humanities
dc.contributor.yokidN/A
dc.contributor.yokidN/A
dc.date.accessioned2024-11-09T22:50:00Z
dc.date.issued2021
dc.description.abstractWe analyze the effect of further pre-training BERT with different domain specific data as an unsupervised domain adaptation strategy for event extraction. Portability of event extraction models is particularly challenging, with large performance drops affecting data on the same text genres (e.g., news). We present PROTEST-ER, a retrained BERT model for protest event extraction. PROTEST-ER outperforms a corresponding generic BERT on out-of-domain data of 8.1 points. Our best performing models reach 51.91-46.39 F1 across both domains.
dc.description.indexedbyWoS
dc.description.indexedbyScopus
dc.description.openaccessNO
dc.description.sponsorshipEuropean Research Council (ERC) [714868] The authors from Koc University were funded by the European Research Council (ERC) Starting Grant 714868 awarded to Dr. Erdem Yoruk for his project Emerging Welfare.
dc.identifier.doiN/A
dc.identifier.isbn978-1-954085-79-4
dc.identifier.scopus2-s2.0-85119310309
dc.identifier.uriN/A
dc.identifier.urihttps://hdl.handle.net/20.500.14288/6579
dc.identifier.wos694853100004
dc.keywordsComputer science, artificial intelligence
dc.keywordsComputer science, theory and methods
dc.keywordsLinguistics
dc.languageEnglish
dc.publisherAssoc Computational Linguistics-Acl
dc.sourceCase 2021: The 4th Workshop On Challenges And Applications Of Automated Extraction Of Socio-Political Events From Text (Case)
dc.subjectComputer science
dc.subjectArtificial intelligence
dc.subjectLinguistics
dc.titlePROTEST-ER: retraining BERT for protest event extraction
dc.typeConference proceeding
dspace.entity.typePublication
local.contributor.authoridN/A
local.contributor.authorid0000-0003-3003-1783
local.contributor.kuauthorMutlu, Osman
local.contributor.kuauthorHürriyetoğlu, Ali
relation.isOrgUnitOfPublication10f5be47-fab1-42a1-af66-1642ba4aff8e
relation.isOrgUnitOfPublication.latestForDiscovery10f5be47-fab1-42a1-af66-1642ba4aff8e

Files

Collections

Publications without Fulltext