A Unifying Theory of Transition-based and Sequence Labeling Parsing
![Thumbnail](/dspace/bitstream/handle/2183/36615/GomezRodriguez_Carlos_2020_Unifying_theory_transition-based_secuence_lab_parsing.pdf.jpg?sequence=5&isAllowed=y)
Ver/ abrir
Use este enlace para citar
http://hdl.handle.net/2183/36615Coleccións
- OpenAIRE [289]
- GI-LYS - Congresos, conferencias, etc. [59]
Metadatos
Mostrar o rexistro completo do ítemTítulo
A Unifying Theory of Transition-based and Sequence Labeling ParsingData
2020-12Cita bibliográfica
Carlos Gómez-Rodríguez, Michalina Strzyz, and David Vilares. 2020. A Unifying Theory of Transition-based and Sequence Labeling Parsing. In Proceedings of the 28th International Conference on Computational Linguistics, pages 3776–3793, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Resumo
[Absctract]: We define a mapping from transition-based parsing algorithms that read sentences from left to right to sequence labeling encodings of syntactic trees. This not only establishes a theoretical relation between transition-based parsing and sequence-labeling parsing, but also provides a method to obtain new encodings for fast and simple sequence labeling parsing from the many existing transition-based parsers for different formalisms. Applying it to dependency parsing, we implement sequence labeling versions of four algorithms, showing that they are learnable and obtain comparable performance to existing encodings.
Palabras chave
Transition-based Parsing
Sequence Labeling Parsing
Syntactic Trees
Parsing Algorithms
Sequence Labeling Parsing
Syntactic Trees
Parsing Algorithms
Descrición
Held online due to COVID-19. December 2020, Barcelona, Spain
Versión do editor
Dereitos
Atribución 3.0 España