Abstract Sign language can be defined as a combination of hand motion mainly used for communication purposes, especially for the deaf-mute community. More than 5% of the worldwide population (320 million) are concerned by the use of it. Through our work, we aim to provide a mean to automate the process of translation from Arabic sign language to written Arabic, in... Sign language can be defined as a combination of hand motion mainly used for communication purposes, especially for the deaf-mute community. More than 5% of the worldwide population (320 million) are concerned by the use of it. Through our work, we aim to provide a mean to automate the process of translation from Arabic sign language to written Arabic, in the static context. As a first step, we will produce a three-level process, allowing the recognition of static Arabic sign. Read More Read Less

Abstract Kannada is an inflectional, agglutinative and morphologically rich language. Kannada is a relatively free-word order language but in the phrasal construction it behaves like a fixed word order language. In other words, order of words in Kannada sentence is flexible but in a chunk, order of words is fixed. This paper presents a statistical chunker for Kannada language using conditional... Kannada is an inflectional, agglutinative and morphologically rich language. Kannada is a relatively free-word order language but in the phrasal construction it behaves like a fixed word order language. In other words, order of words in Kannada sentence is flexible but in a chunk, order of words is fixed. This paper presents a statistical chunker for Kannada language using conditional random field model. Input for chunker is parts of speech tagged Kannada words. The proposed chunker is trained using Enabling Minority Language Engineering(EMILLE) corpus. The performance of proposed model is tested on stories and novels dataset that are collected from EMILLE corpus. An accuracy of 92.77% and 93.28% is achieved on novels and stories dataset respectively. Read More Read Less

Abstract The proposed method is developed for measuring the textual similarity using WordNet taxonomy and information content. It uses the taxonomy knowledge and merge this information with an n–gram based language model (n = 3). The proposed method considers WordNet synsets for lexical relationships between the words and language model for information content value between the two words of the different class.... The proposed method is developed for measuring the textual similarity using WordNet taxonomy and information content. It uses the taxonomy knowledge and merge this information with an n–gram based language model (n = 3). The proposed method considers WordNet synsets for lexical relationships between the words and language model for information content value between the two words of the different class. Finally, a similarity score is generated between two sentences by measuring maximum weight shortest path of the graph. To evaluate the system SemEval 2015 training dataset is considered and the high correlation coefficient of 0.885 has been achieved. Read More Read Less