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 how the complexity of two different architectures of probing models affects the performance of the Transformers in encoding a wide spectrum of linguistic features. Moreover, we explore how this implicit knowledge varies according to different textual genres and language varieties.
Probing Linguistic Knowledge in Italian Neural Language Models across Language Varieties
Miaschi;Alessio;Brunato;Dominique;Dell'Orletta;Felice;Venturi;Giulia
2022
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 how the complexity of two different architectures of probing models affects the performance of the Transformers in encoding a wide spectrum of linguistic features. Moreover, we explore how this implicit knowledge varies according to different textual genres and language varieties.| Campo DC | Valore | Lingua |
|---|---|---|
| dc.authority.ancejournal | IJCOL | en |
| 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 | b3f88f24-048a-4e43-8ab1-6697b90e068e | * |
| dc.collection.name | 01.01 Articolo in rivista | * |
| dc.contributor.appartenenza | Istituto di linguistica computazionale "Antonio Zampolli" - ILC | * |
| dc.contributor.appartenenza.mi | 918 | * |
| dc.contributor.area | Non assegn | * |
| dc.contributor.area | Non assegn | * |
| dc.contributor.area | Non assegn | * |
| dc.contributor.area | Non assegn | * |
| dc.contributor.area | Non assegn | * |
| dc.contributor.area | Non assegn | * |
| dc.contributor.area | Non assegn | * |
| dc.contributor.area | Non assegn | * |
| dc.date.accessioned | 2024/02/21 03:23:35 | - |
| dc.date.available | 2024/02/21 03:23:35 | - |
| dc.date.firstsubmission | 2025/01/24 14:53:46 | * |
| dc.date.issued | 2022 | - |
| dc.date.submission | 2025/01/24 17:35:57 | * |
| 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 how the complexity of two different architectures of probing models affects the performance of the Transformers in encoding a wide spectrum of linguistic features. Moreover, we explore how this implicit knowledge varies according to different textual genres and language varieties. | - |
| dc.description.affiliations | Department of Computer Science, Università di Pisa; Center for Language and Cognition, University of Groningen; Istituto di Linguistica Computazionale "Antonio Zampolli", CNR, Pisa - ItaliaNLP Lab | - |
| 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.doi | 10.4000/ijcol.965 | en |
| dc.identifier.scopus | 2-s2.0-85205875190 | - |
| dc.identifier.uri | https://hdl.handle.net/20.500.14243/443057 | - |
| dc.identifier.url | http://www.aaccademia.it/ita/scheda-libro?aaref=1518 | en |
| dc.language.iso | eng | en |
| dc.miur.last.status.update | 2025-01-24T13:54:36Z | * |
| dc.relation.firstpage | 25 | en |
| dc.relation.lastpage | 44 | en |
| dc.relation.numberofpages | 20 | en |
| dc.subject.keywords | Neural Language Models | - |
| dc.subject.keywords | Interpretability | - |
| dc.subject.keywords | Language Varieties | - |
| dc.subject.singlekeyword | Neural Language Models | * |
| dc.subject.singlekeyword | Interpretability | * |
| dc.subject.singlekeyword | Language Varieties | * |
| dc.title | Probing Linguistic Knowledge in Italian Neural Language Models across Language Varieties | en |
| dc.type.driver | info:eu-repo/semantics/article | - |
| dc.type.full | 01 Contributo su Rivista::01.01 Articolo in rivista | it |
| dc.type.miur | 262 | - |
| dc.ugov.descaux1 | 469733 | - |
| iris.mediafilter.data | 2025/04/12 03:23:51 | * |
| iris.orcid.lastModifiedDate | 2025/02/05 10:19:13 | * |
| iris.orcid.lastModifiedMillisecond | 1738747153020 | * |
| iris.scopus.extIssued | 2022 | - |
| iris.scopus.extTitle | Probing Linguistic Knowledge in Italian Neural Language Models across Language Varieties | - |
| iris.sitodocente.maxattempts | 1 | - |
| iris.unpaywall.bestoahost | publisher | * |
| iris.unpaywall.bestoaversion | publishedVersion | * |
| iris.unpaywall.doi | 10.4000/ijcol.965 | * |
| iris.unpaywall.hosttype | publisher | * |
| iris.unpaywall.isoa | true | * |
| iris.unpaywall.journalisindoaj | true | * |
| iris.unpaywall.landingpage | https://doi.org/10.4000/ijcol.965 | * |
| iris.unpaywall.license | cc-by-nc-nd | * |
| iris.unpaywall.metadataCallLastModified | 13/02/2026 03:30:51 | - |
| iris.unpaywall.metadataCallLastModifiedMillisecond | 1770949851137 | - |
| iris.unpaywall.oastatus | gold | * |
| iris.unpaywall.pdfurl | https://journals.openedition.org/ijcol/pdf/965 | * |
| scopus.authority.ancejournal | IJCOL###2499-4553 | * |
| scopus.category | 1709 | * |
| scopus.category | 3310 | * |
| scopus.category | 1703 | * |
| scopus.category | 1702 | * |
| scopus.contributor.affiliation | ItaliaNLP Lab | - |
| scopus.contributor.affiliation | ItaliaNLP Lab | - |
| scopus.contributor.affiliation | ItaliaNLP Lab | - |
| scopus.contributor.affiliation | University of Groningen | - |
| scopus.contributor.affiliation | ItaliaNLP Lab | - |
| scopus.contributor.afid | 60028868 | - |
| scopus.contributor.afid | 60008941 | - |
| scopus.contributor.afid | 60008941 | - |
| scopus.contributor.afid | 60010023 | - |
| scopus.contributor.afid | 60008941 | - |
| scopus.contributor.auid | 57211678681 | - |
| scopus.contributor.auid | 55237740200 | - |
| scopus.contributor.auid | 27568199800 | - |
| scopus.contributor.auid | 57220744180 | - |
| scopus.contributor.auid | 57540567000 | - |
| scopus.contributor.country | Italy | - |
| scopus.contributor.country | Italy | - |
| scopus.contributor.country | Italy | - |
| scopus.contributor.country | Netherlands | - |
| scopus.contributor.country | Italy | - |
| scopus.contributor.dptid | 109696702 | - |
| scopus.contributor.dptid | 114087935 | - |
| scopus.contributor.dptid | 114087935 | - |
| scopus.contributor.dptid | 103548396 | - |
| scopus.contributor.dptid | 114087935 | - |
| scopus.contributor.name | Alessio | - |
| scopus.contributor.name | Dominique | - |
| scopus.contributor.name | Giulia | - |
| scopus.contributor.name | Gabriele | - |
| scopus.contributor.name | Felice | - |
| scopus.contributor.subaffiliation | Department of Computer Science;Università di Pisa;Istituto di Linguistica Computazionale “Antonio Zampolli”;CNR; | - |
| scopus.contributor.subaffiliation | Istituto di Linguistica Computazionale “Antonio Zampolli”;CNR; | - |
| scopus.contributor.subaffiliation | Istituto di Linguistica Computazionale “Antonio Zampolli”;CNR; | - |
| scopus.contributor.subaffiliation | Center for Language and Cognition; | - |
| scopus.contributor.subaffiliation | Istituto di Linguistica Computazionale “Antonio Zampolli”;CNR; | - |
| scopus.contributor.surname | Miaschi | - |
| scopus.contributor.surname | Brunato | - |
| scopus.contributor.surname | Venturi | - |
| scopus.contributor.surname | Sarti | - |
| scopus.contributor.surname | Dell’orletta | - |
| scopus.date.issued | 2022 | * |
| scopus.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 how the complexity of two different architectures of probing models affects the performance of the Transformers in encoding a wide spectrum of linguistic features. Moreover, we explore how this implicit knowledge varies according to different textual genres and language varieties. | * |
| scopus.description.allpeopleoriginal | Miaschi A.; Brunato D.; Venturi G.; Sarti G.; Dell'orletta F. | * |
| scopus.differences | scopus.description.allpeopleoriginal | * |
| scopus.differences | scopus.relation.issue | * |
| scopus.differences | scopus.relation.volume | * |
| scopus.document.type | ar | * |
| scopus.document.types | ar | * |
| scopus.identifier.doi | 10.4000/ijcol.965 | * |
| scopus.identifier.eissn | 2499-4553 | * |
| scopus.identifier.pui | 2031364966 | * |
| scopus.identifier.scopus | 2-s2.0-85205875190 | * |
| scopus.journal.sourceid | 21101252471 | * |
| scopus.language.iso | eng | * |
| scopus.publisher.name | Accademia University Press | * |
| scopus.relation.firstpage | 25 | * |
| scopus.relation.issue | 1 | * |
| scopus.relation.lastpage | 44 | * |
| scopus.relation.volume | 8 | * |
| scopus.title | Probing Linguistic Knowledge in Italian Neural Language Models across Language Varieties | * |
| scopus.titleeng | Probing Linguistic Knowledge in Italian Neural Language Models across Language Varieties | * |
| Appare nelle tipologie: | 01.01 Articolo in rivista | |
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
prod_469733-doc_190324.pdf
accesso aperto
Descrizione: Probing_Linguistic_Knowledge_in_Italian_Neural_Language_Models_across_Language_Varieties
Tipologia:
Versione Editoriale (PDF)
Licenza:
Creative commons
Dimensione
1.74 MB
Formato
Adobe PDF
|
1.74 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
