In this paper the UNITOR-HMM-TK system participating in the Spatial Role Labeling task at SemEval 2013 is presented. The spatial roles classification is addressed as a sequence-based word classification problem: the SVM learning algorithm is applied, based on a simple feature modeling and a robust lexical generalization achieved through a Distributional Model of Lexical Semantics. In the identification of spatial relations, roles are combined to generate candidate relations, later verified by a SVM classifier. The Smoothed Partial Tree Kernel is applied, i.e. a convolution kernel that enhances both syntactic and lexical properties of the examples, avoiding the need of a manual feature engineering phase. Finally, results on three of the five tasks of the challenge are reported. c 2013 Association for Computational Linguistics
UNITOR-HMM-TK: Structured Kernel-based learning for Spatial Role Labeling / Bastianelli, Emanuele; D., Croce; R., Basili; Nardi, Daniele. - 2:(2013), pp. 573-579. (Intervento presentato al convegno Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013) tenutosi a Atlanta; United States nel 2013).
UNITOR-HMM-TK: Structured Kernel-based learning for Spatial Role Labeling
BASTIANELLI, EMANUELE
;NARDI, Daniele
2013
Abstract
In this paper the UNITOR-HMM-TK system participating in the Spatial Role Labeling task at SemEval 2013 is presented. The spatial roles classification is addressed as a sequence-based word classification problem: the SVM learning algorithm is applied, based on a simple feature modeling and a robust lexical generalization achieved through a Distributional Model of Lexical Semantics. In the identification of spatial relations, roles are combined to generate candidate relations, later verified by a SVM classifier. The Smoothed Partial Tree Kernel is applied, i.e. a convolution kernel that enhances both syntactic and lexical properties of the examples, avoiding the need of a manual feature engineering phase. Finally, results on three of the five tasks of the challenge are reported. c 2013 Association for Computational LinguisticsFile | Dimensione | Formato | |
---|---|---|---|
VE_2012_11573-670011.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
166.6 kB
Formato
Adobe PDF
|
166.6 kB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.