dc.contributor.author | Vidra, Jonáš | |
dc.contributor.author | Žabokrtský, Zdeněk | |
dc.date.accessioned | 2024-03-04T09:11:39Z | |
dc.date.available | 2024-03-04T09:11:39Z | |
dc.date.issued | 2023 | |
dc.identifier.uri | https://hdl.handle.net/20.500.14178/2316 | |
dc.description.abstract | We present a method for supervised cross-lingual construction of word-formation networks (WFNs). WFNs are resources capturing derivational, compositional and other relations between lexical units in a single language. Current state-of-the-art methods for automatically creating them typically rely on supervised or unsupervised pattern-matching of affixes in string representations of words, with few recent inroads into deep learning. All methods known to us work purely in a monolingual setting, limiting the use of higher-quality supervised models to high-resource languages.In this paper, we present two methods, one based on cross-lingual word alignments and translation and another based on cross-lingual word embeddings and neural networks. Both methods are capable of transfer of WFNs into languages for which no word-formational data are available. We evaluate our models on manually-annotated word-formation data from the Universal Derivations and UniMorph projects. | en |
dc.language.iso | en | |
dc.relation.url | https://doi.org/10.14712/00326585.027 | |
dc.rights | Creative Commons Uveďte původ-Neužívejte dílo komerčně-Nezpracovávejte 3.0 Unported | cs |
dc.rights | Creative Commons Attribution-NonCommercial-NoDerivativeWorks 3.0 Unported | en |
dc.title | Transferring Word-Formation Networks Between Languages | en |
dcterms.accessRights | openAccess | |
dcterms.license | https://creativecommons.org/licenses/by-nc-nd/3.0/legalcode | |
dc.date.updated | 2024-03-04T09:11:39Z | |
dc.subject.keyword | word formation | en |
dc.subject.keyword | multilinguality | en |
dc.subject.keyword | wordnet | en |
dc.relation.fundingReference | info:eu-repo/grantAgreement/MSM//EF19_073/0016935 | |
dc.relation.fundingReference | info:eu-repo/grantAgreement/UK/COOP/COOP | |
dc.date.embargoStartDate | 2024-03-04 | |
dc.type.obd | 73 | |
dc.type.version | info:eu-repo/semantics/publishedVersion | |
dc.identifier.doi | 10.14712/00326585.027 | |
dc.identifier.obd | 643344 | |
dc.subject.rivPrimary | 10000::10200::10201 | |
dcterms.isPartOf.name | The Prague Bulletin of Mathematical Linguistics | |
dcterms.isPartOf.issn | 0032-6585 | |
dcterms.isPartOf.journalYear | 2023 | |
dcterms.isPartOf.journalVolume | Neuveden | |
dcterms.isPartOf.journalIssue | 120 | |
uk.faculty.primaryId | 116 | |
uk.faculty.primaryName | Matematicko-fyzikální fakulta | cs |
uk.faculty.primaryName | Faculty of Mathematics and Physics | en |
uk.department.primaryId | 1297 | |
uk.department.primaryName | Ústav formální a aplikované lingvistiky | cs |
uk.department.primaryName | Institute of Formal and Applied Linguistics | en |
dc.description.pageRange | 47-71 | |
dc.type.obdHierarchyCs | ČLÁNEK V ČASOPISU::článek v časopisu::původní článek | cs |
dc.type.obdHierarchyEn | JOURNAL ARTICLE::journal article::original article | en |
dc.type.obdHierarchyCode | 73::152::206 | en |
uk.displayTitle | Transferring Word-Formation Networks Between Languages | en |