A Transition-Based Algorithm for Unrestricted AMR Parsing
Use este enlace para citar
http://hdl.handle.net/2183/36705Colecciones
- OpenAIRE [365]
- GI-LYS - Congresos, conferencias, etc. [71]
Metadatos
Mostrar el registro completo del ítemTítulo
A Transition-Based Algorithm for Unrestricted AMR ParsingFecha
2018-06Cita bibliográfica
David Vilares and Carlos Gómez-Rodríguez. 2018. A Transition-Based Algorithm for Unrestricted AMR Parsing. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 142–149, New Orleans, Louisiana. Association for Computational Linguistics.
Resumen
[Absctract]: Non-projective parsing can be useful to handle cycles and reentrancy in AMR graphs. We explore this idea and introduce a greedy left-to-right non-projective transition-based parser. At each parsing configuration, an oracle decides whether to create a concept or whether to connect a pair of existing concepts. The algorithm handles reentrancy and arbitrary cycles natively, i.e. within the transition system itself. The model is evaluated on the LDC2015E86 corpus, obtaining results close to the state of the art, including a Smatch of 64%, and showing good behavior on reentrant edges.
Palabras clave
Transition-Based Algorithm
Unrestricted AMR parsing
Covington parsing algorithm
Non-Projective Parsing
Reentrancy Handling
Unrestricted AMR parsing
Covington parsing algorithm
Non-Projective Parsing
Reentrancy Handling
Descripción
The Conference was held in New Orleans, June 1 to June 6, 2018 at the Hyatt Regency New Orleans hotel.
Versión del editor
Derechos
Atribución 3.0 España