The Gender Cross-Genre (GxG) task is a shared task on author profiling (in terms of gender) on Italian texts, with a specific focus on cross-genre performance. This task has been proposed for the first time at EVALITA 2018, providing different datasets from different textual genres: Twitter, YouTube, Children writing, Journalism, Personal diaries. Results from a total of 50 different runs show that the task is difficult to learn in itself: while almost all runs beat a 50% baseline, no model reaches an accuracy above 70%. We also observe that cross-genre modelling yields a drop in performance, but not as substantial as one would expect.
Overview of the Evalita 2018 cross-genre gender prediction (GXG) task
Dell'Orletta F;
2018
Abstract
The Gender Cross-Genre (GxG) task is a shared task on author profiling (in terms of gender) on Italian texts, with a specific focus on cross-genre performance. This task has been proposed for the first time at EVALITA 2018, providing different datasets from different textual genres: Twitter, YouTube, Children writing, Journalism, Personal diaries. Results from a total of 50 different runs show that the task is difficult to learn in itself: while almost all runs beat a 50% baseline, no model reaches an accuracy above 70%. We also observe that cross-genre modelling yields a drop in performance, but not as substantial as one would expect.| Campo DC | Valore | Lingua |
|---|---|---|
| dc.authority.anceserie | CEUR WORKSHOP PROCEEDINGS | - |
| dc.authority.anceserie | CEUR Workshop Proceedings | - |
| dc.authority.people | Dell'Orletta F | it |
| dc.authority.people | Nissim M | it |
| 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 02:43:27 | - |
| dc.date.available | 2024/02/21 02:43:27 | - |
| dc.date.issued | 2018 | - |
| dc.description.abstracteng | The Gender Cross-Genre (GxG) task is a shared task on author profiling (in terms of gender) on Italian texts, with a specific focus on cross-genre performance. This task has been proposed for the first time at EVALITA 2018, providing different datasets from different textual genres: Twitter, YouTube, Children writing, Journalism, Personal diaries. Results from a total of 50 different runs show that the task is difficult to learn in itself: while almost all runs beat a 50% baseline, no model reaches an accuracy above 70%. We also observe that cross-genre modelling yields a drop in performance, but not as substantial as one would expect. | - |
| dc.description.affiliations | ItaliaNLP Lab, ILC-CNR, Pisa, , Italy; CLCG, University of Groningen, , Netherlands | - |
| dc.description.allpeople | Dell'Orletta, F; Nissim, M | - |
| dc.description.allpeopleoriginal | Dell'Orletta F.; Nissim M. | - |
| dc.description.fulltext | none | en |
| dc.description.numberofauthors | 2 | - |
| dc.identifier.doi | 10.4000/books.aaccademia.4478 | - |
| dc.identifier.isbn | 9788831978422 | - |
| dc.identifier.scopus | 2-s2.0-85058613848 | - |
| dc.identifier.uri | https://hdl.handle.net/20.500.14243/392544 | - |
| dc.identifier.url | http://www.scopus.com/record/display.url?eid=2-s2.0-85058613848&origin=inward | - |
| dc.language.iso | eng | - |
| dc.relation.conferencedate | 12-13/12/2018 | - |
| dc.relation.conferencename | 6th conferenza EVALITA '18, Evaluation of NLP and Speech Tools for Italian | - |
| dc.relation.conferenceplace | Torino | - |
| dc.relation.volume | 2263 | - |
| dc.subject.keywords | authorship profiling | - |
| dc.subject.singlekeyword | authorship profiling | * |
| dc.title | Overview of the Evalita 2018 cross-genre gender prediction (GXG) task | 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.type.referee | Sì, ma tipo non specificato | - |
| dc.ugov.descaux1 | 434875 | - |
| iris.orcid.lastModifiedDate | 2024/04/04 12:35:50 | * |
| iris.orcid.lastModifiedMillisecond | 1712226950576 | * |
| iris.scopus.extIssued | 2018 | - |
| iris.scopus.extTitle | Overview of the Evalita 2018 cross-genre gender prediction (GXG) task | - |
| iris.scopus.metadataErrorDescription | 400 Bad Request: " Document ID is not valid |
- |
| iris.scopus.metadataErrorType | APPLICATION | - |
| iris.scopus.metadataStatus | ERROR | - |
| iris.sitodocente.maxattempts | 3 | - |
| iris.unpaywall.bestoahost | publisher | * |
| iris.unpaywall.bestoaversion | publishedVersion | * |
| iris.unpaywall.doi | 10.4000/books.aaccademia.4478 | * |
| iris.unpaywall.hosttype | publisher | * |
| iris.unpaywall.isoa | true | * |
| iris.unpaywall.journalisindoaj | false | * |
| iris.unpaywall.landingpage | https://doi.org/10.4000/books.aaccademia.4478 | * |
| iris.unpaywall.license | cc-by-nc-nd | * |
| iris.unpaywall.metadataCallLastModified | 17/12/2025 06:03:20 | - |
| iris.unpaywall.metadataCallLastModifiedMillisecond | 1765947800227 | - |
| iris.unpaywall.oastatus | hybrid | * |
| scopus.authority.anceserie | CEUR WORKSHOP PROCEEDINGS###1613-0073 | * |
| scopus.category | 1700 | * |
| scopus.contributor.affiliation | ILC-CNR | - |
| scopus.contributor.affiliation | University of Groningen | - |
| scopus.contributor.afid | 60021199 | - |
| scopus.contributor.afid | 60010023 | - |
| scopus.contributor.auid | 57540567000 | - |
| scopus.contributor.auid | 8281949100 | - |
| scopus.contributor.country | Italy | - |
| scopus.contributor.country | Netherlands | - |
| scopus.contributor.dptid | 121833164 | - |
| scopus.contributor.dptid | - | |
| scopus.contributor.name | Felice | - |
| scopus.contributor.name | Malvina | - |
| scopus.contributor.subaffiliation | ItaliaNLP Lab; | - |
| scopus.contributor.subaffiliation | CLCG; | - |
| scopus.contributor.surname | Dell’Orletta | - |
| scopus.contributor.surname | Nissim | - |
| scopus.date.issued | 2018 | * |
| scopus.description.abstract | The Gender Cross-Genre (GxG) task is a shared task on author profiling (in terms of gender) on Italian texts, with a specific focus on cross-genre performance. This task has been proposed for the first time at EVALITA 2018, providing different datasets from different textual genres: Twitter, YouTube, Children writing, Journalism, Personal diaries. Results from a total of 50 different runs show that the task is difficult to learn in itself: while almost all runs beat a 50% baseline, no model reaches an accuracy above 70%. We also observe that cross-genre modelling yields a drop in performance, but not as substantial as one would expect. | * |
| scopus.description.allpeopleoriginal | Dell'Orletta F.; Nissim M. | * |
| scopus.differences | scopus.relation.conferencename | * |
| scopus.differences | scopus.authority.anceserie | * |
| scopus.differences | scopus.publisher.name | * |
| scopus.differences | scopus.relation.conferencedate | * |
| scopus.differences | scopus.relation.conferenceplace | * |
| scopus.document.type | cp | * |
| scopus.document.types | cp | * |
| scopus.funding.funders | 100009436 - Library and Information Technology Association; | * |
| scopus.identifier.doi | 10.4000/books.aaccademia.4478 | * |
| scopus.identifier.pui | 625515220 | * |
| scopus.identifier.scopus | 2-s2.0-85058613848 | * |
| scopus.journal.sourceid | 21100218356 | * |
| scopus.language.iso | eng | * |
| scopus.publisher.name | CEUR-WS | * |
| scopus.relation.conferencedate | 2018 | * |
| scopus.relation.conferencename | 6th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop, EVALITA 2018 | * |
| scopus.relation.conferenceplace | ita | * |
| scopus.relation.volume | 2263 | * |
| scopus.title | Overview of the Evalita 2018 cross-genre gender prediction (GXG) task | * |
| scopus.titleeng | Overview of the Evalita 2018 cross-genre gender prediction (GXG) task | * |
| Appare nelle tipologie: | 04.01 Contributo in Atti di convegno | |
File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
