Dependency parsing with bottom-up Hierarchical Pointer Networks
Use este enlace para citar
http://hdl.handle.net/2183/32906
Excepto si se señala otra cosa, la licencia del ítem se describe como Atribución-NoComercial-SinDerivadas 4.o Internacional
Colecciones
- GI-LYS - Artigos [51]
- OpenAIRE [366]
Metadatos
Mostrar el registro completo del ítemTítulo
Dependency parsing with bottom-up Hierarchical Pointer NetworksFecha
2023-03Cita bibliográfica
Fernández-González, Daniel; Gómez-Rodríguez, Carlos (2023): Dependency parsing with bottom-up Hierarchical Pointer Networks. Information Fusion 91: 494-503
Resumen
[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.
Palabras clave
Natural language processing
Computational linguistics
Parsing
Dependency parsing
Neural networks
Deep learning
Computational linguistics
Parsing
Dependency parsing
Neural networks
Deep learning
Descripción
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG
Versión del editor
Derechos
Atribución-NoComercial-SinDerivadas 4.o Internacional
ISSN
1872-6305