Edit Page
The edit can be undone. Please check the comparison below to verify that this is what you want to do, and then publish the changes below to finish undoing the edit.
Latest revision | Your text | ||
Line 1: | Line 1: | ||
− | Supervised training |
+ | Supervised training makes parsers prone to error propagation (McDonald & Nivre, 2007) since the model is under-trained on errorneous states. This has induced a line of research on dynamic oracles (Goldberg & Nivre, 2012<ref name=Goldberg.Nivre12>Goldberg, Y., & Nivre, J. (2012). A Dynamic Oracle for Arc-Eager Dependency Parsing. Proceedings of the 24th International Conference on Computational Linguistics (COLING), 2(December), 959–976.</ref>; |
Goldberg & Nirve, 2013<ref name=goldberg.nivre13>Goldberg, Y., & Nivre, J. (2013). Training Deterministic Parsers with Non-Deterministic Oracles. Transactions of the Association of Computational Linguistics -- Volume 1, 403–414.</ref>; |
Goldberg & Nirve, 2013<ref name=goldberg.nivre13>Goldberg, Y., & Nivre, J. (2013). Training Deterministic Parsers with Non-Deterministic Oracles. Transactions of the Association of Computational Linguistics -- Volume 1, 403–414.</ref>; |
||
Goldberg et al., 2014<ref>Goldberg, Y., Sartorio, F., & Satta, G. (2014). A tabular method for dynamic oracles in transition-based parsing. Transactions of the Association for Computational Linguistics, 2, 119–130.</ref>; |
Goldberg et al., 2014<ref>Goldberg, Y., Sartorio, F., & Satta, G. (2014). A tabular method for dynamic oracles in transition-based parsing. Transactions of the Association for Computational Linguistics, 2, 119–130.</ref>; |