Semantic role labeling systems are often designed as inductive processes over annotated resources. Supervised algorithms based on complex grammatical information achieve state-of-the-art accuracy. However, their generalization on the argument classification task is poorer, as large performance drops in out-of-domain tests showed. In this paper, a robust method based on a minimal set of grammatical features and a distributional model of lexical semantic information is proposed. The achievable generalization ability is studied in several training conditions where negligible performance drops are observed. © 2009 IEEE.
Giannone, C., Croce, D., Basili, R. (2009). Semantic word spaces for robust role labeling. In 8th International Conference on Machine Learning and Applications, ICMLA 2009 (pp.261-266) [10.1109/ICMLA.2009.117].
Semantic word spaces for robust role labeling
CROCE, DANILO;BASILI, ROBERTO
2009-12-01
Abstract
Semantic role labeling systems are often designed as inductive processes over annotated resources. Supervised algorithms based on complex grammatical information achieve state-of-the-art accuracy. However, their generalization on the argument classification task is poorer, as large performance drops in out-of-domain tests showed. In this paper, a robust method based on a minimal set of grammatical features and a distributional model of lexical semantic information is proposed. The achievable generalization ability is studied in several training conditions where negligible performance drops are observed. © 2009 IEEE.File | Dimensione | Formato | |
---|---|---|---|
icmla09_v1.6.pdf
solo utenti autorizzati
Licenza:
Copyright dell'editore
Dimensione
297.64 kB
Formato
Adobe PDF
|
297.64 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.