Translating Italian connectives into Italian Sign Language

Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, pages 270–280, Sofia, Bulgaria, August 4-9 2013. c⃝2013 Association for Computational Linguistics Translating Italian connectives into Italian Sign Language Camillo Lugaresi University of Illinois at Chicago Politecnico di Milano clugar2@uic.edu Barbara Di Eugenio Department of Computer Science University of Illinois at Chicago bdieugen@uic.edu Abstract We present a corpus analysis of how Ital- ian connectives are translated into LIS, the Italian Sign Language. Since corpus re- sources are scarce, we propose an align- ment method between the syntactic trees of the Italian sentence and of its LIS trans- lation. This method, and clustering ap- plied to its outputs, highlight the differ- ent ways a connective can be rendered in LIS: with a corresponding sign, by affect- ing the location or shape of other signs, or being omitted altogether. We translate these findings into a computational model that will be integrated into the pipeline of an existing Italian-LIS rendering system. Initial experiments to learn the four possi- ble translations with Decision Trees give promising results. 1 Introduction Automatic translation between a spoken language and a signed language gives rise to some of the same difficulties as translation between spoken languages, but adds unique challenges of its own. Contrary to what one might expect, sign languages are not artificial languages, but natural languages that spontaneously arose within deaf communities; although they are typically named after the region where they are used, they are not derived from the local spoken language and tend to bear no similar- ity to it. Therefore, translation from any spoken language into the signed language of that specific region is at least as complicated as between any pairs of unrelated languages. The problem of automatic translation is com- pounded by the fact that the amount of computa- tional resources to draw on is much smaller than is typical for major spoken languages. Moreover, the fact that sign languages employ a different transmission modality (gestures and expressions instead of sounds) means that existing writing sys- tems are not easily adaptable to them. The result- ing lack of a shared written form does nothing to improve the availability of sign language corpora; bilingual corpora, which are of particular impor- tance to a translation system, are especially rare. In fact, various projects around the world are try- ing to ameliorate this sad state of affairs for spe- cific Sign Languages (Lu and Huenerfauth, 2010; Braffort et al., 2010; Morrissey et al., 2010). In this paper, we describe the work we per- formed as concerns the translation of connectives from the Italian language into LIS, the Italian Sign Language (Lingua Italiana dei Segni). Because the communities of signers in Italy are relatively small and fragmented, and the language has a relatively short history, there is far less existing research and material to draw on than for, say, ASL (American Sign Language) or BSL (British Sign Language). Our work was undertaken within the purview of the ATLAS project (Bertoldi et al., 2010; …

Content truncated to 500 words