Mostrar o rexistro simple do ítem

dc.contributor.authorMuñoz-Ortiz, Alberto
dc.contributor.authorVilares, David
dc.date.accessioned2024-05-22T12:49:19Z
dc.date.available2024-05-22T12:49:19Z
dc.date.issued2023-07
dc.identifier.citationAlberto Muñoz-Ortiz and David Vilares. 2023. Another Dead End for Morphological Tags? Perturbed Inputs and Parsing. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7301–7310, Toronto, Canada. Association for Computational Linguistics.es_ES
dc.identifier.urihttp://hdl.handle.net/2183/36574
dc.descriptionToronto, Canada from July 9th to July 14th, 2023es_ES
dc.description.abstract[Absctract]: The usefulness of part-of-speech tags for parsing has been heavily questioned due to the success of word-contextualized parsers. Yet, most studies are limited to coarse-grained tags and high quality written content; while we know little about their influence when it comes to models in production that face lexical errors. We expand these setups and design an adversarial attack to verify if the use of morphological information by parsers: (i) contributes to error propagation or (ii) if on the other hand it can play a role to correct mistakes that word-only neural parsers make. The results on 14 diverse UD treebanks show that under such attacks, for transition- and graph-based models their use contributes to degrade the performance even faster, while for the (lower-performing) sequence labeling parsers they are helpful. We also show that if morphological tags were utopically robust against lexical perturbations, they would be able to correct parsing mistakes.es_ES
dc.description.sponsorshipThis paper has received funding from grant SCANNER-UDC (PID2020-113230RB-C21) funded by MCIN/AEI/10.13039/501100011033, the European Research Council (ERC), which has supported this research under the European Union’s Horizon Europe research and innovation programme (SALSA, grant agreement No 101100615), Xunta de Galicia (ED431C 2020/11), and Centro de Investigación de Galicia “CITIC”, funded by Xunta de Galicia and the European Union (ERDF - Galicia 2014-2020 Program), by grant ED431G 2019/01es_ES
dc.description.sponsorshipXunta de Galicia; ED431C2020/11es_ES
dc.description.sponsorshipXunta de Galicia; ED431G 2019/01es_ES
dc.language.isoenges_ES
dc.publisherAssociation for Computational Linguisticses_ES
dc.relationinfo:eu-repo/grantAgreement/EC/HE/101100615es_ES
dc.relationinfo:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2020-113230RB-C21/ES/MODELOS MULTITAREA DE ETIQUETADO SECUENCIAL PARA EL RECONOCIMIENTO DE ENTIDADES ENRIQUECIDO CON INFORMACIÓN LINGÜÍSTICA: SINTAXIS E INTEGRACIÓN MULTITAREA (SCANNER-UDC)es_ES
dc.relation.urihttps://aclanthology.org/2023.findings-acl.459/es_ES
dc.rightsAtribución 3.0 Españaes_ES
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/es/*
dc.subjectPart-of-speech tagses_ES
dc.subjectWord-contextualized parserses_ES
dc.subjectMorphological tagses_ES
dc.subjectAdversarial attackses_ES
dc.titleAnother Dead End for Morphological Tags? Perturbed Inputs and Parsinges_ES
dc.typeinfo:eu-repo/semantics/conferenceObjectes_ES
dc.typeinfo:eu-repo/semantics/conferenceObjectes_ES
dc.rights.accessinfo:eu-repo/semantics/openAccesses_ES
UDC.journalTitleFindings of the Association for Computational Linguistics: ACL 2023es_ES
UDC.startPage7301es_ES
UDC.endPage7310es_ES
UDC.conferenceTitleThe 61st Annual Meeting of the Association for Computational Linguistics (ACL’23)es_ES


Ficheiros no ítem

Thumbnail
Thumbnail

Este ítem aparece na(s) seguinte(s) colección(s)

Mostrar o rexistro simple do ítem