On the Transferability of Neural Models of Morphological Analogies

Simple item page
dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorAlsaidi, Safaen_US
dc.contributor.authorDecker, Amandineen_US
dc.contributor.authorLay, Puthineathen_US
dc.contributor.authorMarquer, Estebanen_US
dc.contributor.authorMurena, Pierre-Alexandreen_US
dc.contributor.authorCouceiro, Miguelen_US
dc.contributor.departmentDepartment of Computer Scienceen
dc.contributor.groupauthorProbabilistic Machine Learningen
dc.contributor.groupauthorProfessorship Kaski Samuelen
dc.contributor.organizationUniversité de Lorraineen_US
dc.date.accessioned2021-12-31T13:56:19Z
dc.date.available2021-12-31T13:56:19Z
dc.date.issued2021-09en_US
dc.description| openaire: EC/H2020/952215/EU//TAILOR
dc.description.abstractAnalogical proportions are statements expressed in the form "A is to B as C is to D" and are used for several reasoning and classification tasks in artificial intelligence and natural language processing (NLP). In this paper, we focus on morphological tasks and we propose a deep learning approach to detect morphological analogies. We present an empirical study to see how our framework transfers across languages, and that highlights interesting similarities and differences between these languages. In view of these results, we also discuss the possibility of building a multilingual morphological model.en
dc.description.versionPeer revieweden
dc.identifier.citationAlsaidi, S, Decker, A, Lay, P, Marquer, E, Murena, P-A & Couceiro, M 2021, On the Transferability of Neural Models of Morphological Analogies. in Machine Learning and Principles and Practice of Knowledge Discovery in Databases : International Workshops of ECML PKDD 2021, Virtual Event, September 13-17, 2021, Proceedings, Part II. Communications in Computer and Information Science, vol. 1524, Springer, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Virtual, Online, 13/09/2021. https://doi.org/10.1007/978-3-030-93736-2_7en
dc.identifier.doi10.1007/978-3-030-93736-2_7en_US
dc.identifier.isbn9783030937355
dc.identifier.isbn978-3-030-93736-2
dc.identifier.issn1865-0929
dc.identifier.otherPURE UUID: 3debbad4-6a9f-43e0-a0ab-e16631913e55en_US
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/3debbad4-6a9f-43e0-a0ab-e16631913e55en_US
dc.identifier.otherPURE LINK: https://hal.inria.fr/INRIA/hal-03313591v1en_US
dc.identifier.otherPURE LINK: https://arxiv.org/pdf/2108.03938.pdfen_US
dc.identifier.otherPURE LINK: https://link.springer.com/book/9783030937331en_US
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/111963
dc.identifier.urnURN:NBN:fi:aalto-2021123111103
dc.language.isoenen
dc.relationinfo:eu-repo/grantAgreement/EC/H2020/952215/EU//TAILORen_US
dc.relation.ispartofEuropean Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databasesen
dc.relation.ispartofseriesMachine Learning and Principles and Practice of Knowledge Discovery in Databases: International Workshops of ECML PKDD 2021, Virtual Event, September 13-17, 2021, Proceedings, Part IIen
dc.relation.ispartofseriesCommunications in Computer and Information Science ; Volume 1524en
dc.rightsopenAccessen
dc.titleOn the Transferability of Neural Models of Morphological Analogiesen
dc.typeA4 Artikkeli konferenssijulkaisussafi

Files

Collections

[article-cris] Perustieteiden korkeakoulu / SCI