Publication:
Transformers analyzing poetry: multilingual metrical pattern prediction with transfomer-based language models

Simple item page
dc.contributor.authorRosa, Javier de la
dc.contributor.authorPérez Pozo, Álvaro
dc.contributor.authorSisto, Mirella de
dc.contributor.authorHernández, Laura
dc.contributor.authorDíaz, Aitor
dc.contributor.authorRos, Salvador
dc.contributor.authorGonzález Blanco, Elena
dc.contributor.funderHorizon 2020 Framework Programme
dc.contributor.funderEuropean Commission
dc.contributor.rorhttps://ror.org/02jjdwm75
dc.date.accessioned2024-07-08T13:15:03Z
dc.date.available2024-07-08T13:15:03Z
dc.date.issued2023
dc.description.abstractThe splitting of words into stressed and unstressed syllables is the foundation for the scansion of poetry,a process that aims at determining the metrical pattern of a line of verse within a poem. Intricate language rules and their exceptions,as well as poetic licenses exerted by the authors,make calculating these patterns a nontrivial task. Some rhetorical devices shrink the metrical length,while others might extend it. This opens the door for interpretation and further complicates the creation of automated scansion algorithms useful for automatically analyzing corpora on a distant reading fashion. In this paper,we compare the automated metrical pattern identification systems available for Spanish,English,and German,against fine-tuned monolingual and multilingual language models trained on the same task. Despite being initially conceived as models suitable for semantic tasks,our results suggest that transformers-based models retain enough structural information to perform reasonably well for Spanish on a monolingual setting,and outperforms both for English and German when using a model trained on the three languages,showing evidence of the benefits of cross-lingual transfer between the languages. © 2021,The Author(s).
dc.description.fundingtypeSee http://postdata.linhd.uned.es/ . Starting Grant research project Poetry Standardization and Linked Open Data: POSTDATA (ERC-2015-STG-679528) funded by the European Research Council (https://erc.europa.eu) (ERC) under the research and innovation program Horizon2020 of the European Union. This research was supported by the project Poetry Standardization and Linked Open Data (POSTDATA) (ERC-2015-STG-679528) obtained by Elena González-Blanco and funded by an European Research Council ( https://erc.europa.eu ) Starting Grant under the Horizon2020 Program of the European Union. This research was supported by the project Poetry Standardization and Linked Open Data (POSTDATA) (ERC-2015-STG-679528) obtained by Elena González-Blanco and funded by an European Research Council (https://erc.europa.eu) Starting Grant under the Horizon2020 Program of the European Union.
dc.description.keywordDigital humanities
dc.description.keywordLanguage models
dc.description.keywordNatural language processing
dc.description.keywordPoetry
dc.formatapplication/pdf
dc.identifier.citationDe la Rosa, J., Pérez, Á., De Sisto, M., Hernández, L., Díaz, A., Ros, S., & González-Blanco, E. (2023). Transformers analyzing poetry: multilingual metrical pattern prediction with transfomer-based language models. Neural Computing and Applications, 1-6.
dc.identifier.doihttps://doi.org/10.1007/s00521-021-06692-2
dc.identifier.issn9410643
dc.identifier.officialurlhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85119484453&doi=10.1007%2fs00521-021-06692-2&partnerID=40&md5=841b8f12c5044537de5920989364e7c2
dc.identifier.urihttps://hdl.handle.net/20.500.14417/3136
dc.issue.number25
dc.journal.titleNeural Computing and Applications
dc.language.isoeng
dc.page.final18176
dc.page.initial18171
dc.page.total23
dc.publisherSpringer Science and Business Media Deutschland GmbH
dc.relation.entityIE University
dc.relation.projectIDH2020: 679528 
dc.relation.schoolIE School of Science & Technology
dc.rightsAttribution 4,0 International
dc.rights.accessRightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectDigital humanities; Language models; Natural language processing; Poetry
dc.subject.keywordDigital humanities
dc.subject.keywordLanguage models
dc.subject.keywordNatural language processing
dc.subject.keywordPoetry
dc.subject.otherComputational linguistics
dc.subject.otherNatural language processing systems
dc.subject.otherDistant readings
dc.subject.otherLanguage processing
dc.subject.otherNatural languages
dc.subject.otherNon-trivial tasks
dc.subject.otherPattern identification
dc.subject.otherSplittings
dc.subject.otherSemantics
dc.titleTransformers analyzing poetry: multilingual metrical pattern prediction with transfomer-based language models
dc.typeinfo:eu-repo/semantics/article
dc.version.typeinfo:eu-repo/semantics/publishedVersion
dc.volume.number35
dspace.entity.typePublication
person.identifier.scopus-author-id55203236600
person.identifier.scopus-author-id57222025738
person.identifier.scopus-author-id57224541472
person.identifier.scopus-author-id57222031867
person.identifier.scopus-author-id57348530700
person.identifier.scopus-author-id7005158730
person.identifier.scopus-author-id57190153324
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Transformers analyzing poetry multilingual metrical pattern prediction with transfomer-based language models.pdf
Size:
234.85 KB
Format:
Adobe Portable Document Format
Download
Collections
Research Articles