Mostrar o rexistro simple do ítem
Dependency parsing with bottom-up Hierarchical Pointer Networks
dc.contributor.author | Fernández-González, Daniel | |
dc.contributor.author | Gómez-Rodríguez, Carlos | |
dc.date.accessioned | 2023-04-21T08:08:21Z | |
dc.date.available | 2023-04-21T08:08:21Z | |
dc.date.issued | 2023-03 | |
dc.identifier.citation | Fernández-González, Daniel; Gómez-Rodríguez, Carlos (2023): Dependency parsing with bottom-up Hierarchical Pointer Networks. Information Fusion 91: 494-503 | es_ES |
dc.identifier.issn | 1872-6305 | |
dc.identifier.uri | http://hdl.handle.net/2183/32906 | |
dc.description | Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG | es_ES |
dc.description.abstract | [Abstract] Dependency parsing is a crucial step towards deep language understanding and, therefore, widely demanded by numerous Natural Language Processing applications. In particular, left-to-right and top-down transition-based algorithms that rely on Pointer Networks are among the most accurate approaches for performing dependency parsing. Additionally, it has been observed for the top-down algorithm that Pointer Networks’ sequential decoding can be improved by implementing a hierarchical variant, more adequate to model dependency structures. Considering all this, we develop a bottom-up oriented Hierarchical Pointer Network for the left-to-right parser and propose two novel transition-based alternatives: an approach that parses a sentence in right-to-left order and a variant that does so from the outside in. We empirically test the proposed neural architecture with the different algorithms on a wide variety of languages, outperforming the original approach in practically all of them and setting new state-of-the-art results on the English and Chinese Penn Treebanks for non-contextualized and BERT-based embeddings. | es_ES |
dc.description.sponsorship | Ministerio de Ciencia e Innovación;PID2020-113230RB-C21 | es_ES |
dc.description.sponsorship | Xunta de Galicia;ED431C2020/11 | es_ES |
dc.description.sponsorship | European Regional Developmet Fund;ED431G 2019/01 | es_ES |
dc.language.iso | eng | es_ES |
dc.publisher | Elsevier | es_ES |
dc.relation | info:eu-repo/grantAgreement/EC/H2020/714150 | es_ES |
dc.relation | info:eu-repo/grantAgreement/EC/H2020/101100615 | es_ES |
dc.relation.uri | http://dx.doi.org/10.1016/j.inffus.2022.10.023 | es_ES |
dc.rights | Atribución-NoComercial-SinDerivadas 4.o Internacional | es_ES |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ | * |
dc.subject | Natural language processing | es_ES |
dc.subject | Computational linguistics | es_ES |
dc.subject | Parsing | es_ES |
dc.subject | Dependency parsing | es_ES |
dc.subject | Neural networks | es_ES |
dc.subject | Deep learning | es_ES |
dc.title | Dependency parsing with bottom-up Hierarchical Pointer Networks | es_ES |
dc.type | info:eu-repo/semantics/article | es_ES |
dc.rights.access | info:eu-repo/semantics/openAccess | es_ES |
UDC.journalTitle | Information Fusion | es_ES |
UDC.volume | 91 | es_ES |
UDC.startPage | 494 | es_ES |
UDC.endPage | 503 | es_ES |
Ficheiros no ítem
Este ítem aparece na(s) seguinte(s) colección(s)
-
GI-LYS - Artigos [51]
-
OpenAIRE [359]