We present a four-step hierarchical SRL strategy with generalized the classical two-level approach(boudary detection and classification). To achieve this, we have split the classification step by grouping together roles which share linguistic properties (e.g. Core Roles versus Adjuncts). The results show that the nonoptimized hierarchical approach is computationaly more efficient than the traditional systems and it preserves their accuracy.
Hierarchical Semantic Role Labeling
Coppola, Bonaventura;
2005-01-01
Abstract
We present a four-step hierarchical SRL strategy with generalized the classical two-level approach(boudary detection and classification). To achieve this, we have split the classification step by grouping together roles which share linguistic properties (e.g. Core Roles versus Adjuncts). The results show that the nonoptimized hierarchical approach is computationaly more efficient than the traditional systems and it preserves their accuracy.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
