The paper presents the preliminary results of a research project focused on the creation and the annotation of one Italian Sign Language corpus concerning the weather forecasts domain. As a result of the annotation process, our annotations of signs sequences showed that the semantics of the signed discourse cannot be grasped just through an annotation of single weather signs which exploits the five parameters handshape, movements, directions, locations and non-manual components. Rather, from the annotation process appears that, in order to grasp the discourse semantics, it is necessary to consider the extensive use of Highly Iconic Structures in order to specify the iconic properties of the different atmospherics phenomena. In particular, it often occurs that several signs are combined among themselves (see also Cuxac, 2000; Di Renzo, et al, 2006; Pizzuto et al., 2008; Pizzuto, Rossini & Russo, 2006). Thus, respect to single signs, our analysis of complex manual and non-manual units stored in our database suggests the necessity to better explore multidimensional aspects, in order to properly develop and train an automatic translator able to translate from Italian written text to Italian Sign Language.
ATLAS Project: Forecast in Italian Sign Language and Annotation of Corpora
VENDRAME, Mara;
2010-01-01
Abstract
The paper presents the preliminary results of a research project focused on the creation and the annotation of one Italian Sign Language corpus concerning the weather forecasts domain. As a result of the annotation process, our annotations of signs sequences showed that the semantics of the signed discourse cannot be grasped just through an annotation of single weather signs which exploits the five parameters handshape, movements, directions, locations and non-manual components. Rather, from the annotation process appears that, in order to grasp the discourse semantics, it is necessary to consider the extensive use of Highly Iconic Structures in order to specify the iconic properties of the different atmospherics phenomena. In particular, it often occurs that several signs are combined among themselves (see also Cuxac, 2000; Di Renzo, et al, 2006; Pizzuto et al., 2008; Pizzuto, Rossini & Russo, 2006). Thus, respect to single signs, our analysis of complex manual and non-manual units stored in our database suggests the necessity to better explore multidimensional aspects, in order to properly develop and train an automatic translator able to translate from Italian written text to Italian Sign Language.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
