Mostrar o rexistro simple do ítem
4 and 7-bit Labeling for Projective and Non-Projective Dependency Trees
dc.contributor.author | Gómez-Rodríguez, Carlos | |
dc.contributor.author | Roca Rodríguez, Diego | |
dc.contributor.author | Vilares, David | |
dc.date.accessioned | 2024-05-22T09:14:26Z | |
dc.date.available | 2024-05-22T09:14:26Z | |
dc.date.issued | 2023-12 | |
dc.identifier.citation | Carlos Gómez-Rodríguez, Diego Roca, and David Vilares. 2023. 4 and 7-bit Labeling for Projective and Non-Projective Dependency Trees. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 6375–6384, Singapore. Association for Computational Linguistics. | es_ES |
dc.identifier.uri | http://hdl.handle.net/2183/36571 | |
dc.description | Singapore from Dec 6th to Dec 10th, 2023. | es_ES |
dc.description.abstract | [Absctract]: We introduce an encoding for parsing as sequence labeling that can represent any projective dependency tree as a sequence of 4-bit labels, one per word. The bits in each word’s label represent (1) whether it is a right or left dependent, (2) whether it is the outermost (left/right) dependent of its parent, (3) whether it has any left children and (4) whether it has any right children. We show that this provides an injective mapping from trees to labels that can be encoded and decoded in linear time. We then define a 7-bit extension that represents an extra plane of arcs, extending the coverage to almost full non-projectivity (over 99.9% empirical arc coverage). Results on a set of diverse treebanks show that our 7-bit encoding obtains substantial accuracy gains over the previously best-performing sequence labeling encodings. | es_ES |
dc.description.sponsorship | This work has received funding by the European Research Council (ERC), under the Horizon Europe research and innovation programme (SALSA, grant agreement No 101100615), ERDF/MICINN-AEI (SCANNER-UDC, PID2020- 113230RB-C21), Xunta de Galicia (ED431C 2020/11), Grant GAP (PID2022-139308OA-I00) funded by MCIN/AEI/10.13039/501100011033/ and by ERDF “A way of making Europe”, and Centro de Investigación de Galicia “CITIC”, funded by the Xunta de Galicia through the collaboration agreement between the Consellería de Cultura, Educación, Formación Profesional e Universidades and the Galician universities for the reinforcement of the research centres of the Galician University System (CIGUS). | es_ES |
dc.description.sponsorship | Xunta de Galicia; ED431C2020/11 | es_ES |
dc.language.iso | eng | es_ES |
dc.publisher | Association for Computational Linguistics | es_ES |
dc.relation.uri | https://aclanthology.org/2023.emnlp-main.393/ | es_ES |
dc.rights | Atribución 3.0 España | es_ES |
dc.rights.uri | http://creativecommons.org/licenses/by/3.0/es/ | * |
dc.subject | Dependency parsing | es_ES |
dc.subject | Sequence labeling | es_ES |
dc.subject | Projective and non-projective dependency trees | es_ES |
dc.title | 4 and 7-bit Labeling for Projective and Non-Projective Dependency Trees | es_ES |
dc.type | conference output | es_ES |
dc.rights.accessRights | open access | es_ES |
UDC.journalTitle | Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing | es_ES |
UDC.startPage | 6375 | es_ES |
UDC.endPage | 6384 | es_ES |
UDC.conferenceTitle | 2023 Conference on Empirical Methods in Natural Language (EMNLP 2023) | es_ES |
UDC.coleccion | Investigación | es_ES |
UDC.departamento | Letras | es_ES |
UDC.grupoInv | Lingua e Sociedade da Información (LYS) | es_ES |
dc.relation.projectID | info:eu-repo/grantAgreement/EC/HE/101100615 | es_ES |
dc.relation.projectID | 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.projectID | info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/PID2022-1393080A-100/ES/REPRESENTACIONES ESTRUCTURADAS VERDES Y ENCHUFABLES | es_ES |
Ficheiros no ítem
Este ítem aparece na(s) seguinte(s) colección(s)
-
Investigación (FFIL) [860]