Mostrar o rexistro simple do ítem
Parsing linearizations appreciate PoS tags - but some are fussy about errors
dc.contributor.author | Muñoz-Ortiz, Alberto | |
dc.contributor.author | Anderson, Mark | |
dc.contributor.author | Vilares, David | |
dc.contributor.author | Gómez-Rodríguez, Carlos | |
dc.date.accessioned | 2024-05-27T12:11:41Z | |
dc.date.available | 2024-05-27T12:11:41Z | |
dc.date.issued | 2022-11 | |
dc.identifier.citation | Alberto Muñoz-Ortiz, Mark Anderson, David Vilares, and Carlos Gómez-Rodríguez. 2022. Parsing linearizations appreciate PoS tags - but some are fussy about errors. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 117–127, Online only. Association for Computational Linguistics. | es_ES |
dc.identifier.uri | http://hdl.handle.net/2183/36646 | |
dc.description | It was held in Taipei, China. Nov 21, 2022 - Nov 23, 2022 | es_ES |
dc.description.abstract | [Absctract]: PoS tags, once taken for granted as a useful resource for syntactic parsing, have become more situational with the popularization of deep learning. Recent work on the impact of PoS tags on graph- and transition-based parsers suggests that they are only useful when tagging accuracy is prohibitively high, or in low-resource scenarios. However, such an analysis is lacking for the emerging sequence labeling parsing paradigm, where it is especially relevant as some models explicitly use PoS tags for encoding and decoding. We undertake a study and uncover some trends. Among them, PoS tags are generally more useful for sequence labeling parsers than for other paradigms, but the impact of their accuracy is highly encoding-dependent, with the PoS-based head-selection encoding being best only when both tagging accuracy and resource availability are high. | es_ES |
dc.description.sponsorship | Mark was supported by a UKRI Future Leaders Fellowship (MR/T042001/1). This paper has received funding from ERDF/MICINN-AEI (SCANNERUDC, PID2020-113230RB-C21), Xunta de Galicia (ED431C 2020/11), and Centro de Investigacion de ´ Galicia “CITIC”, funded by Xunta de Galicia and the European Union (ERDF - Galicia 2014-2020 Program), by grant ED431G 2019/01 | es_ES |
dc.description.sponsorship | Xunta de Galicia; ED431C 2020/11 | es_ES |
dc.description.sponsorship | Xunta de Galicia; ED431G 2019/01 | es_ES |
dc.language.iso | eng | es_ES |
dc.publisher | Association for Computational Linguistics | es_ES |
dc.relation | info: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.uri | https://aclanthology.org/2022.aacl-short.16/ | es_ES |
dc.rights | Atribución 3.0 España | es_ES |
dc.rights.uri | http://creativecommons.org/licenses/by/3.0/es/ | * |
dc.subject | Part-of-Speech Tags | es_ES |
dc.subject | Sequence Labeling Parsing | es_ES |
dc.subject | POS tags | es_ES |
dc.subject | Syntactic Parsing | es_ES |
dc.subject | Tagging Accuracy | es_ES |
dc.subject | POS tags | es_ES |
dc.title | Parsing linearizations appreciate PoS tags - but some are fussy about errors | es_ES |
dc.type | info:eu-repo/semantics/conferenceObject | es_ES |
dc.type | info:eu-repo/semantics/conferenceObject | es_ES |
dc.rights.access | info:eu-repo/semantics/openAccess | es_ES |
UDC.journalTitle | Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers) | es_ES |
UDC.startPage | 117 | es_ES |
UDC.endPage | 127 | es_ES |
UDC.conferenceTitle | 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (AACL-IJCNLP 2022) | es_ES |