Show simple item record

dc.contributor.authorKagan Akkaya, E
dc.contributor.authorCan, Burcu
dc.date.accessioned2020-09-08T12:53:22Z
dc.date.available2020-09-08T12:53:22Z
dc.date.issued2020-01-28
dc.identifier.citationKağan Akkaya, E., & Can, B. (2020). Transfer learning for Turkish named entity recognition on noisy text. Natural Language Engineering, 1-30. doi:10.1017/S1351324919000627en
dc.identifier.issn1351-3249en
dc.identifier.doi10.1017/S1351324919000627en
dc.identifier.urihttp://hdl.handle.net/2436/623614
dc.descriptionThis is an accepted manuscript of an article published by Cambridge University Press in Natural Language Engineering on 28/01/2020, available online: https://doi.org/10.1017/S1351324919000627 The accepted version of the publication may differ from the final published version.en
dc.description.abstract© Cambridge University Press 2020. In this article, we investigate using deep neural networks with different word representation techniques for named entity recognition (NER) on Turkish noisy text. We argue that valuable latent features for NER can, in fact, be learned without using any hand-crafted features and/or domain-specific resources such as gazetteers and lexicons. In this regard, we utilize character-level, character n-gram-level, morpheme-level, and orthographic character-level word representations. Since noisy data with NER annotation are scarce for Turkish, we introduce a transfer learning model in order to learn infrequent entity types as an extension to the Bi-LSTM-CRF architecture by incorporating an additional conditional random field (CRF) layer that is trained on a larger (but formal) text and a noisy text simultaneously. This allows us to learn from both formal and informal/noisy text, thus improving the performance of our model further for rarely seen entity types. We experimented on Turkish as a morphologically rich language and English as a relatively morphologically poor language. We obtained an entity-level F1 score of 67.39% on Turkish noisy data and 45.30% on English noisy data, which outperforms the current state-of-art models on noisy text. The English scores are lower compared to Turkish scores because of the intense sparsity in the data introduced by the user writing styles. The results prove that using subword information significantly contributes to learning latent features for morphologically rich languages.en
dc.formatapplication/pdfen
dc.languageen
dc.language.isoenen
dc.publisherCambridge University Press (CUP)en
dc.relation.urlhttps://www.cambridge.org/core/journals/natural-language-engineering/article/transfer-learning-for-turkish-named-entity-recognition-on-noisy-text/C05743D10C34CD76502B5B34487FEB03en
dc.subjectnamed entity recognitionen
dc.subjecttransfer learningen
dc.subjectrecurrent neural networksen
dc.subjectlow-resource languageen
dc.subjectnoisy texten
dc.titleTransfer learning for Turkish named entity recognition on noisy texten
dc.typeJournal articleen
dc.identifier.eissn1469-8110
dc.identifier.journalNatural Language Engineeringen
dc.date.updated2020-08-26T08:23:58Z
dc.date.accepted2019-11-11
rioxxterms.funderHacettepe Universityen
rioxxterms.identifier.projectUOW08092020BCen
rioxxterms.versionAMen
rioxxterms.licenseref.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/en
rioxxterms.licenseref.startdate2020-09-08en
dc.source.volume27
dc.source.issue1
dc.source.beginpage35
dc.source.endpage64
dc.description.versionPublished version
refterms.dateFCD2020-09-08T12:52:08Z
refterms.versionFCDAM
refterms.dateFOA2020-09-08T00:00:00Z


Files in this item

Thumbnail
Name:
Can_Transfer_Learning_For_2020.pdf
Size:
1.432Mb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record

https://creativecommons.org/licenses/by-nc-nd/4.0/
Except where otherwise noted, this item's license is described as https://creativecommons.org/licenses/by-nc-nd/4.0/