Syntax-aware Transformers for Neural Machine Translation: The Case of Text to Sign Gloss Translation
Universitat Pompeu Fabra, Spain, Santiago Egea Gómez, Euan McGill, Universitat Pompeu Fabra, Spain, Horacio Saggion, Universitat Pompeu Fabra, Spain
Abstract
It is well-established that the preferred mode of communication of the deaf and hard of hearing (DHH) community are Sign Languages (SLs), but they are considered low resource languages where natural language processing technologies are of concern. In this paper we study the problem of text to SL gloss Machine Translation (MT) using Transformer-based architectures. Despite the significant advances of MT for spoken languages in the recent couple of decades, MT is in its infancy when it comes to SLs. We enrich a Transformer-based architecture aggregating syntactic information extracted from a dependency parser to wordembeddings. We test our model on a wellknown dataset showing that the syntax-aware model obtains performance gains in terms of MT evaluation metrics.