In this paper we present an in-depth investigation of the linguistic knowledge encoded by the transformer models currently available for the Italian language. In particular, we investigate whether and how using different architectures of probing models affects the performance of Italian transformers in encoding a wide spectrum of linguistic features. Moreover, we explore how this implicit knowledge varies according to different textual genres.

Italian Transformers Under the Linguistic Lens

Miaschi;Alessio;Brunato;Dominique;Dell'Orletta;Felice;Venturi;Giulia
2020

Abstract

In this paper we present an in-depth investigation of the linguistic knowledge encoded by the transformer models currently available for the Italian language. In particular, we investigate whether and how using different architectures of probing models affects the performance of Italian transformers in encoding a wide spectrum of linguistic features. Moreover, we explore how this implicit knowledge varies according to different textual genres.
Campo DC Valore Lingua
dc.authority.orgunit Istituto di linguistica computazionale "Antonio Zampolli" - ILC en
dc.authority.people Miaschi en
dc.authority.people Alessio en
dc.authority.people Sarti en
dc.authority.people Gabriele en
dc.authority.people Brunato en
dc.authority.people Dominique en
dc.authority.people Dell'Orletta en
dc.authority.people Felice en
dc.authority.people Venturi en
dc.authority.people Giulia en
dc.collection.id.s 71c7200a-7c5f-4e83-8d57-d3d2ba88f40d *
dc.collection.name 04.01 Contributo in Atti di convegno *
dc.contributor.appartenenza Istituto di linguistica computazionale "Antonio Zampolli" - ILC *
dc.contributor.appartenenza.mi 918 *
dc.date.accessioned 2024/02/21 06:02:50 -
dc.date.available 2024/02/21 06:02:50 -
dc.date.firstsubmission 2024/12/18 17:22:05 *
dc.date.issued 2020 -
dc.date.submission 2024/12/18 17:22:05 *
dc.description.abstracteng In this paper we present an in-depth investigation of the linguistic knowledge encoded by the transformer models currently available for the Italian language. In particular, we investigate whether and how using different architectures of probing models affects the performance of Italian transformers in encoding a wide spectrum of linguistic features. Moreover, we explore how this implicit knowledge varies according to different textual genres. -
dc.description.affiliations Università di Pisa; Università di Trieste; Istituto di Linguistica Computazionale (ILC-CNR) -
dc.description.allpeople Miaschi, Alessio; Miaschi, Alessio; Sarti, ; Gabriele, ; Brunato, DOMINIQUE PIERINA; Brunato, DOMINIQUE PIERINA; Dell'Orletta, Felice; Dell'Orletta, Felice; Venturi, Giulia; Venturi, Giulia -
dc.description.allpeopleoriginal Miaschi, Alessio and Sarti, Gabriele and Brunato, Dominique and Dell'Orletta, Felice and Venturi, Giulia en
dc.description.fulltext open en
dc.description.numberofauthors 10 -
dc.identifier.isbn 979-12-80136-28-2 en
dc.identifier.uri https://hdl.handle.net/20.500.14243/421765 -
dc.identifier.url http://ceur-ws.org/Vol-2769/paper_56.pdf en
dc.language.iso eng en
dc.miur.last.status.update 2024-12-18T16:22:22Z *
dc.relation.conferencedate 01-03/03/2021 en
dc.relation.conferencename Seventh Italian Conference on Computational Linguistics (CLiC-it) en
dc.relation.ispartofbook Proceedings of the Seventh Italian Conference on Computational Linguistics (CLiC-it) en
dc.subject.keywords nlp -
dc.subject.keywords neural language models -
dc.subject.keywords interpretability -
dc.subject.singlekeyword nlp *
dc.subject.singlekeyword neural language models *
dc.subject.singlekeyword interpretability *
dc.title Italian Transformers Under the Linguistic Lens en
dc.type.driver info:eu-repo/semantics/conferenceObject -
dc.type.full 04 Contributo in convegno::04.01 Contributo in Atti di convegno it
dc.type.miur 273 -
dc.ugov.descaux1 442038 -
iris.mediafilter.data 2025/04/15 04:01:45 *
iris.orcid.lastModifiedDate 2024/12/19 16:49:15 *
iris.orcid.lastModifiedMillisecond 1734623355319 *
iris.scopus.extIssued 2020 -
iris.scopus.extTitle Italian transformers under the linguistic lens -
iris.sitodocente.maxattempts 1 -
Appare nelle tipologie: 04.01 Contributo in Atti di convegno
File in questo prodotto:
File Dimensione Formato  
paper_56.pdf

accesso aperto

Licenza: Creative commons
Dimensione 1.42 MB
Formato Adobe PDF
1.42 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.14243/421765
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact