We study the impact of a new multi-task learning approach in deep neural network for polarity and irony detection in Italian Twitter posts. We compare this approach with traditional single-task learning models. The different behavior of the two approaches shows the effectiveness of the proposed method that is able to combine the information from the two tasks improving the accuracy in both tasks. This is particularly true on edge cases in which knowledge about the two tasks is needed to classify a tweet, this is the case, for example, when the literal polarity of a tweet is inverted by irony.
Multi-task learning in deep neural network for sentiment polarity and irony classification
Cimino A;Dell'Orletta F
2018
Abstract
We study the impact of a new multi-task learning approach in deep neural network for polarity and irony detection in Italian Twitter posts. We compare this approach with traditional single-task learning models. The different behavior of the two approaches shows the effectiveness of the proposed method that is able to combine the information from the two tasks improving the accuracy in both tasks. This is particularly true on edge cases in which knowledge about the two tasks is needed to classify a tweet, this is the case, for example, when the literal polarity of a tweet is inverted by irony.| Campo DC | Valore | Lingua |
|---|---|---|
| dc.authority.anceserie | CEUR WORKSHOP PROCEEDINGS | - |
| dc.authority.anceserie | CEUR Workshop Proceedings | - |
| dc.authority.people | De Mattei L | it |
| dc.authority.people | Cimino A | it |
| dc.authority.people | Dell'Orletta F | 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 | 2024/02/20 17:17:51 | - |
| dc.date.available | 2024/02/20 17:17:51 | - |
| dc.date.issued | 2018 | - |
| dc.description.abstracteng | We study the impact of a new multi-task learning approach in deep neural network for polarity and irony detection in Italian Twitter posts. We compare this approach with traditional single-task learning models. The different behavior of the two approaches shows the effectiveness of the proposed method that is able to combine the information from the two tasks improving the accuracy in both tasks. This is particularly true on edge cases in which knowledge about the two tasks is needed to classify a tweet, this is the case, for example, when the literal polarity of a tweet is inverted by irony. | - |
| dc.description.affiliations | Dipartimento di Informatica, Università di Pisa, Italy; Istituto di Linguistica Computazionale Antonio Zampolli (ILC-CNR), Pisa, Italy | - |
| dc.description.allpeople | De Mattei L.; Cimino A.; Dell'Orletta F. | - |
| dc.description.allpeopleoriginal | De Mattei L.; Cimino A.; Dell'Orletta F. | - |
| dc.description.fulltext | none | en |
| dc.description.numberofauthors | 1 | - |
| dc.identifier.scopus | 2-s2.0-85057857671 | - |
| dc.identifier.uri | https://hdl.handle.net/20.500.14243/392584 | - |
| dc.identifier.url | http://www.scopus.com/record/display.url?eid=2-s2.0-85057857671&origin=inward | - |
| dc.language.iso | eng | - |
| dc.relation.conferencedate | 22-23/11/2018 | - |
| dc.relation.conferencename | 2nd Workshop on Natural Language for Artificial Intelligence (NL4AI) | - |
| dc.relation.conferenceplace | Trento | - |
| dc.relation.firstpage | 76 | - |
| dc.relation.lastpage | 82 | - |
| dc.relation.volume | 2244 | - |
| dc.subject.keywords | Multi-Task Learning | - |
| dc.subject.keywords | Deep Neural Network | - |
| dc.subject.keywords | Sentiment Analysis | - |
| dc.subject.singlekeyword | Multi-Task Learning | * |
| dc.subject.singlekeyword | Deep Neural Network | * |
| dc.subject.singlekeyword | Sentiment Analysis | * |
| dc.title | Multi-task learning in deep neural network for sentiment polarity and irony classification | 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 | 434915 | - |
| iris.orcid.lastModifiedDate | 2024/03/15 08:57:57 | * |
| iris.orcid.lastModifiedMillisecond | 1710489477867 | * |
| iris.scopus.extIssued | 2018 | - |
| iris.scopus.extTitle | Multi-task learning in deep neural network for sentiment polarity and irony classification | - |
| iris.sitodocente.maxattempts | 2 | - |
| scopus.authority.anceserie | CEUR WORKSHOP PROCEEDINGS###1613-0073 | * |
| scopus.category | 1700 | * |
| scopus.contributor.affiliation | Istituto di Linguistica Computazionale Antonio Zampolli (ILC-CNR) | - |
| scopus.contributor.affiliation | Istituto di Linguistica Computazionale Antonio Zampolli (ILC-CNR) | - |
| scopus.contributor.affiliation | Istituto di Linguistica Computazionale Antonio Zampolli (ILC-CNR) | - |
| scopus.contributor.afid | 60008941 | - |
| scopus.contributor.afid | 60008941 | - |
| scopus.contributor.afid | 60008941 | - |
| scopus.contributor.auid | 57204921228 | - |
| scopus.contributor.auid | 57002803800 | - |
| scopus.contributor.auid | 57540567000 | - |
| scopus.contributor.country | Italy | - |
| scopus.contributor.country | Italy | - |
| scopus.contributor.country | Italy | - |
| scopus.contributor.dptid | - | |
| scopus.contributor.dptid | - | |
| scopus.contributor.dptid | - | |
| scopus.contributor.name | Lorenzo | - |
| scopus.contributor.name | Andrea | - |
| scopus.contributor.name | Felice | - |
| scopus.contributor.subaffiliation | - | |
| scopus.contributor.subaffiliation | - | |
| scopus.contributor.subaffiliation | - | |
| scopus.contributor.surname | De Mattei | - |
| scopus.contributor.surname | Cimino | - |
| scopus.contributor.surname | Dell'Orletta | - |
| scopus.date.issued | 2018 | * |
| scopus.description.abstracteng | We study the impact of a new multi-task learning approach in deep neural network for polarity and irony detection in Italian Twitter posts. We compare this approach with traditional single-task learning models. The different behavior of the two approaches shows the effectiveness of the proposed method that is able to combine the information from the two tasks improving the accuracy in both tasks. This is particularly true on edge cases in which knowledge about the two tasks is needed to classify a tweet, this is the case, for example, when the literal polarity of a tweet is inverted by irony. | * |
| scopus.description.allpeopleoriginal | De Mattei L.; Cimino A.; Dell'Orletta F. | * |
| scopus.differences | scopus.relation.conferencename | * |
| scopus.differences | scopus.authority.anceserie | * |
| scopus.differences | scopus.publisher.name | * |
| scopus.differences | scopus.subject.keywords | * |
| scopus.differences | scopus.relation.conferencedate | * |
| scopus.differences | scopus.relation.conferenceplace | * |
| scopus.document.type | cp | * |
| scopus.document.types | cp | * |
| scopus.identifier.pui | 625315874 | * |
| scopus.identifier.scopus | 2-s2.0-85057857671 | * |
| scopus.journal.sourceid | 21100218356 | * |
| scopus.language.iso | eng | * |
| scopus.publisher.name | CEUR-WS | * |
| scopus.relation.conferencedate | 2018 | * |
| scopus.relation.conferencename | 2nd Workshop on Natural Language for Artificial Intelligence, NL4AI 2018 | * |
| scopus.relation.conferenceplace | ita | * |
| scopus.relation.firstpage | 76 | * |
| scopus.relation.lastpage | 82 | * |
| scopus.relation.volume | 2244 | * |
| scopus.subject.keywords | Deep neural network; Multi-Task learning; Sentiment analysis; | * |
| scopus.title | Multi-task learning in deep neural network for sentiment polarity and irony classification | * |
| scopus.titleeng | Multi-task learning in deep neural network for sentiment polarity and irony classification | * |
| 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.
