Sequence Tagging for Fast Dependency Parsing
Use este enlace para citar
http://hdl.handle.net/2183/25103Colecciones
- GI-LYS - Congresos, conferencias, etc. [71]
- OpenAIRE [368]
Metadatos
Mostrar el registro completo del ítemTítulo
Sequence Tagging for Fast Dependency ParsingFecha
2019Cita bibliográfica
Strzyz, M.; Vilares, D.; Gómez-Rodríguez, C. Sequence Tagging for Fast Dependency Parsing. Proceedings 2019, 21, 49.
Resumen
[Abstract]
Dependency parsing has been built upon the idea of using parsing methods based on shift-reduce or graph-based algorithms in order to identify binary dependency relations between the words in a sentence. In this study we adopt a radically different approach and cast full dependency parsing as a pure sequence tagging task. In particular, we apply a linearization function to the tree that results in an output label for each token that conveys information about the word’s dependency relations. We then follow a supervised strategy and train a bidirectional long short-term memory network to learn to predict such linearized trees. Contrary to the previous studies attempting this, the results show that this approach not only leads to accurate but also fast dependency parsing. Furthermore, we obtain even faster and more accurate parsers by recasting the problem as multitask learning, with a twofold objective: to reduce the output vocabulary and also to exploit hidden patterns coming from a second parsing paradigm (constituent grammars) when used as an auxiliary task.
Palabras clave
Natural language processing
Parsing
Sequence labeling
Tagging
Multitask learning
Parsing
Sequence labeling
Tagging
Multitask learning
Versión del editor
Derechos
Atribution 4.0 International
ISSN
2504-3900