In this paper we present ULISSE, an unsupervised linguistically--driven algorithm to select reliable parses from the output of a dependency parser. Different experiments were devised to show that the algorithm is robust enough to deal with the output of different parsers and with different languages, as well as to be used across different domains. In all cases, ULISSE appears to outperform the baseline algorithms.
ULISSE: an unsupervised algorithm for detecting reliable dependency parses
Felice Dell'Orletta;Giulia Venturi;Simonetta Montemagni
2011
Abstract
In this paper we present ULISSE, an unsupervised linguistically--driven algorithm to select reliable parses from the output of a dependency parser. Different experiments were devised to show that the algorithm is robust enough to deal with the output of different parsers and with different languages, as well as to be used across different domains. In all cases, ULISSE appears to outperform the baseline algorithms.| Campo DC | Valore | Lingua |
|---|---|---|
| dc.authority.orgunit | Istituto di linguistica computazionale "Antonio Zampolli" - ILC | - |
| dc.authority.people | Felice Dell'Orletta | it |
| dc.authority.people | Giulia Venturi | it |
| dc.authority.people | Simonetta Montemagni | 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 20:55:05 | - |
| dc.date.available | 2024/02/20 20:55:05 | - |
| dc.date.issued | 2011 | - |
| dc.description.abstracteng | In this paper we present ULISSE, an unsupervised linguistically--driven algorithm to select reliable parses from the output of a dependency parser. Different experiments were devised to show that the algorithm is robust enough to deal with the output of different parsers and with different languages, as well as to be used across different domains. In all cases, ULISSE appears to outperform the baseline algorithms. | - |
| dc.description.affiliations | CNR-ILC | - |
| dc.description.allpeople | Dell'Orletta, Felice; Venturi, Giulia; Montemagni, Simonetta | - |
| dc.description.allpeopleoriginal | Felice Dell'Orletta, Giulia Venturi and Simonetta Montemagni | - |
| dc.description.fulltext | none | en |
| dc.description.note | ID_PUMA: cnr.ilc/2011-A2-006 | - |
| dc.description.numberofauthors | 3 | - |
| dc.identifier.isbn | 978-1-932432-92-3 | - |
| dc.identifier.uri | https://hdl.handle.net/20.500.14243/214925 | - |
| dc.identifier.url | http://dl.acm.org/citation.cfm?id=2018950 | - |
| dc.language.iso | eng | - |
| dc.miur.last.status.update | 2024-12-16T11:59:11Z | * |
| dc.relation.conferencedate | 23-24 Giugno 2011 | - |
| dc.relation.conferencename | CoNLL '11 Proceedings of the Fifteenth Conference on Computational Natural Language Learning | - |
| dc.relation.conferenceplace | Portland, Oregon, USA | - |
| dc.relation.firstpage | 115 | - |
| dc.relation.lastpage | 124 | - |
| dc.relation.numberofpages | 9 | - |
| dc.subject.keywords | Dependency Parsing | - |
| dc.subject.keywords | Selection of Reliable Parses | - |
| dc.subject.keywords | Unsupervised Algorithm | - |
| dc.subject.singlekeyword | Dependency Parsing | * |
| dc.subject.singlekeyword | Selection of Reliable Parses | * |
| dc.subject.singlekeyword | Unsupervised Algorithm | * |
| dc.title | ULISSE: an unsupervised algorithm for detecting reliable dependency parses | 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 | 205505 | - |
| iris.orcid.lastModifiedDate | 2024/04/04 11:28:43 | * |
| iris.orcid.lastModifiedMillisecond | 1712222923647 | * |
| iris.sitodocente.maxattempts | 10 | - |
| 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.
