Multitask Pointer Network for Multi-Representational Parsing
Use este enlace para citar
http://hdl.handle.net/2183/29887
A non ser que se indique outra cousa, a licenza do ítem descríbese como Atribución 4.0 Internacional
Coleccións
- GI-LYS - Artigos [51]
- OpenAIRE [359]
Metadatos
Mostrar o rexistro completo do ítemTítulo
Multitask Pointer Network for Multi-Representational ParsingData
2022-01-25Cita bibliográfica
Daniel Fernández-González, Carlos Gómez-Rodríguez, Multitask Pointer Network for multi-representational parsing, Knowledge-Based Systems, Volume 236, 2022, 107760, ISSN 0950-7051, https://doi.org/10.1016/j.knosys.2021.107760. (https://www.sciencedirect.com/science/article/pii/S0950705121009849)
Resumo
[Abstract] Dependency and constituent trees are widely used by many artificial intelligence applications for representing the syntactic structure of human languages. Typically, these structures are separately produced by either dependency or constituent parsers. In this article, we propose a transition-based approach that, by training a single model, can efficiently parse any input sentence with both constituent and dependency trees, supporting both continuous/projective and discontinuous/non-projective syntactic structures. To that end, we develop a Pointer Network architecture with two separate task-specific decoders and a common encoder, and follow a multitask learning strategy to jointly train them. The resulting quadratic system, not only becomes the first parser that can jointly produce both unrestricted constituent and dependency trees from a single model, but also proves that both syntactic formalisms can benefit from each other during training, achieving state-of-the-art accuracies in several widely-used benchmarks such as the continuous English and Chinese Penn Treebanks, as well as the discontinuous German NEGRA and TIGER datasets.
Palabras chave
Natural language processing
Computational linguistics
Parsing
Dependency parsing
Constituent parsing
Neural networks
Deep learning
Computational linguistics
Parsing
Dependency parsing
Constituent parsing
Neural networks
Deep learning
Descrición
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG
Versión do editor
Dereitos
Atribución 4.0 Internacional
ISSN
0950-7051