Universal Access in the Information Society ( IF 2.4 ) Pub Date : 2019-11-13 , DOI: 10.1007/s10209-019-00695-6 Hamzah Luqman , Sabri A. Mahmoud
Arabic sign language (ArSL) is one of the sign languages that is used in Arab countries. This language has structure and grammar that differ from spoken Arabic. Available ArSL recognition systems perform direct mapping between the recognized sign in the ArSL sentence and its corresponding Arabic word. This results in persevering the structure and grammar of the ArSL sentence. ArSL translation involves converting the recognized ArSL sentence into Arabic sentence that meets the structure and grammar of Arabic. We propose in this work a rule-based machine translation system between ArSL and Arabic. The proposed system performs morphological and syntactic analysis to translate the ArSL sentence lexically and syntactically into Arabic. To evaluate this work, we perform manual and automatic evaluation using a corpus on the health domain. The obtained results show that our translation system provides an accurate translation for more than 80% of the translated sentences.
中文翻译:
从阿拉伯手语到阿拉伯语的机器翻译系统
阿拉伯手语(ArSL)是阿拉伯国家/地区使用的手语之一。该语言的结构和语法与阿拉伯语不同。可用的ArSL识别系统在ArSL句子中识别的符号与其对应的阿拉伯语单词之间执行直接映射。这导致坚持了ArSL句子的结构和语法。ArSL翻译涉及将公认的ArSL句子转换为符合阿拉伯语结构和语法的阿拉伯语句子。我们在这项工作中提出了ArSL和阿拉伯语之间基于规则的机器翻译系统。拟议的系统执行形态和句法分析,以将ArSL句子从词法和句法上翻译成阿拉伯语。为了评估这项工作,我们使用健康领域的语料库执行手动和自动评估。