Publication:
AfriKI: machine-in-the-loop Afrikaans poetry generation

Simple item page
dc.contributor.coauthorBaş, Anıl
dc.contributor.departmentDepartment of Comparative Literature
dc.contributor.kuauthorvan Heerden, Imke
dc.contributor.kuprofileOther
dc.contributor.otherDepartment of Comparative Literature
dc.contributor.schoolcollegeinstituteCollege of Social Sciences and Humanities
dc.contributor.yokid318142
dc.date.accessioned2024-11-09T12:28:29Z
dc.date.issued2021
dc.description.abstractThis paper proposes a generative language model called AfriKI. Our approach is based on an LSTM architecture trained on a small corpus of contemporary fiction. With the aim of promoting human creativity, we use the model as an authoring tool to explore machine-in-the-loop Afrikaans poetry generation. To our knowledge, this is the first study to attempt creative text generation in Afrikaans.
dc.description.fulltextYES
dc.description.indexedbyScopus
dc.description.openaccessYES
dc.description.publisherscopeInternational
dc.description.sponsoredbyTubitakEuTÜBİTAK
dc.description.sponsorshipScientific and Technological Research Council of Turkey (TÜBİTAK)
dc.description.versionPublisher version
dc.formatpdf
dc.identifier.embargoNO
dc.identifier.filenameinventorynoIR03425
dc.identifier.isbn9.78195E+12
dc.identifier.linkhttps://aclanthology.org/2021.hcinlp-1.12
dc.identifier.quartileN/A
dc.identifier.scopus2-s2.0-85123319896
dc.identifier.urihttps://hdl.handle.net/20.500.14288/1811
dc.keywordsComputational linguistics
dc.keywordsNatural language processing systems
dc.languageEnglish
dc.publisherAssociation for Computational Linguistics (ACL)
dc.relation.grantno118C285
dc.relation.urihttp://cdm21054.contentdm.oclc.org/cdm/ref/collection/IR/id/10223
dc.sourceBridging Human-Computer Interaction and Natural Language Processing, HCINLP 2021 - Proceedings of the 1st Workshop
dc.subjectArtificial intelligence
dc.subjectChinese poetry
dc.subjectLyrics
dc.titleAfriKI: machine-in-the-loop Afrikaans poetry generation
dc.typeConference proceeding
dspace.entity.typePublication
local.contributor.authorid0000-0002-4224-8800
local.contributor.kuauthorvan Heerden, Imke
relation.isOrgUnitOfPublication4d7bb696-a523-4c96-8832-64baef1b8b21
relation.isOrgUnitOfPublication.latestForDiscovery4d7bb696-a523-4c96-8832-64baef1b8b21

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
10223.pdf
Size:
359.64 KB
Format:
Adobe Portable Document Format
Download

Collections

Publications with Fulltext