A rule-based translation from written Spanish to Spanish Sign Language glosses

Abstract

This is the author’s version of a work that was accepted for publication in Computer Speech and Language. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Computer Speech and Language, 28, 3 (2015) DOI: 10.1016/j.csl.2013.10.003One of the aims of Assistive Technologies is to help people with disabilities to communicate with others and to provide means of access to information. As an aid to Deaf people, we present in this work a production-quality rule-based machine system for translating from Spanish to Spanish Sign Language (LSE) glosses, which is a necessary precursor to building a full machine translation system that eventually produces animation output. The system implements a transfer-based architecture from the syntactic functions of dependency analyses. A sketch of LSE is also presented. Several topics regarding translation to sign languages are addressed: the lexical gap, the bootstrapping of a bilingual lexicon, the generation of word order for topic-oriented languages, and the treatment of classifier predicates and classifier names. The system has been evaluated with an open-domain testbed, reporting a 0.30 BLEU (BiLingual Evaluation Understudy) and 42% TER (Translation Error Rate). These results show consistent improvements over a statistical machine translation baseline, and some improvements over the same system preserving the word order in the source sentence. Finally, the linguistic analysis of errors has identified some differences due to a certain degree of structural variation in LSE

A Crowdsourcing-Based Framework for the Development and Validation of Machine Readable Parallel Corpus for Sign Languages

“…The dictionary provides two levels of search in which users can either search a Spanish word against a sign and similarly can do a signed search by giving a Spanish word as input. The Italian sign language dictionary was proposed by [19]. An electronic multimedia dictionary consisting of signs of 3 different sign languages including American Sign Language (ASL), Japanese Sign Language (JSL) and Korean Sign Language (KSL) was created by [20].…”

PE2LGP: tradutor de português europeu para língua gestual portuguesa em glosas

“…Uma versão melhorada da componente de tradução deste sistema tendo em conta fenómenos sintáticos e semânticos da LI-BRAS foi proposta por Lima et al (2015). Outros exemplos, são os trabalhos de tradução de espanhol para Língua Gestual Espanhola (Lengua de Signos Española -LSE) (San-Segundo et al, 2006;Porta et al, 2014), que faz referência a um outro sistema de tradução espanhola para LSE baseado na plataforma Apertium (Forcada et al, 2011); tradução para língua gestual ucraniana em telemóveis (Davydov & Lozynska, 2017), e tradução de textoárabe para língua gestualárabe (Luqman & Mahmoud, 2018). A maioria usa a abordagem baseada na transferência gramatical (transferência sintática, lexical e semântica) através de regras de tradução criadas por linguistas.…”

Bidirectional Machine Translation Between Turkish and Turkish Sign Language : A Data-Driven Approach

“…A is our biggest dataset with size of 2068 translation pairs. With its size it is also one of the biggest datasets in past studies for sign languages regarding [6]. C is a subset of B, and B is a subset of A.…”

“…We observed one other study in past studies covering a translation system between a spoken language and a sign language's glosses. This is a rule-based, unidirectional translation system from Spanish to Spanish Sign Language glosses [6]. They evaluated their system using various datasets each including 195 sentences.…”

“…Some studies prefer to use a mannequin, or an avatar to visualize the output [2] [3][4] [5]. A few of the past studies chose to express the results in glosses [6]. This study aims to put forward a dynamic, bidirectional machine translation system between written Turkish and Turkish Sign Language (TSL) glosses.…”