This paper presents the current development of the first large parallel corpus between Italian and Italian Sign Language (Lingua Italiana dei Segni, LIS). This initiative has been taken within the ATLAS project (Automatic Translation into Sign Languages), that aims at realizing a virtual interpreter, which automatically translates an Italian text into LIS. The Italian-LIS virtual interpreter is implemented by means of two modules interfaced by the ATLAS Extended Written LIS (AEWLIS), which is a translation-oriented representation of LIS: the first module translates the source Italian text into AEWLIS; the second module transforms the AEWLIS content into a coherent LIS sequence, smoothly animated by a virtual character. As no significant amount of electronic data are available for Italian and LIS, we have started building a parallel corpus from scratch in order to train and tune the Italian-AEWLIS translation system, and to compare the resulting virtual animations with human-performed LIS interpretations. The corpus, which will be freely available, actually presents a tri-lingual structure, with the Italian text, the AEWLIS sequence, and the signed LIS video.

On the creation and the annotation of a large-scale Italian-LIS parallel corpus

Bertoldi, Nicola;
2010-01-01

Abstract

This paper presents the current development of the first large parallel corpus between Italian and Italian Sign Language (Lingua Italiana dei Segni, LIS). This initiative has been taken within the ATLAS project (Automatic Translation into Sign Languages), that aims at realizing a virtual interpreter, which automatically translates an Italian text into LIS. The Italian-LIS virtual interpreter is implemented by means of two modules interfaced by the ATLAS Extended Written LIS (AEWLIS), which is a translation-oriented representation of LIS: the first module translates the source Italian text into AEWLIS; the second module transforms the AEWLIS content into a coherent LIS sequence, smoothly animated by a virtual character. As no significant amount of electronic data are available for Italian and LIS, we have started building a parallel corpus from scratch in order to train and tune the Italian-AEWLIS translation system, and to compare the resulting virtual animations with human-performed LIS interpretations. The corpus, which will be freely available, actually presents a tri-lingual structure, with the Italian text, the AEWLIS sequence, and the signed LIS video.
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.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11582/5849
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
social impact