Toward HMM based machine translation for ASL

Author

Boulares, Mehrez ; Jemni, Mohamed

Author_Institution

Res. Lab. of Technol. of Inf. & Commun. & Electr. Ingineering (LaTICE), Ecole Super. des Sci. et Tech. de Tunis, Tunis, Tunisia

fYear

2013

fDate

24-26 Oct. 2013

Firstpage

1

Lastpage

4

Abstract

HMM-based models are widely used in many fields such as pattern recognition, speech recognition or Part-of-speech tagging. However, A HMM can be considered as a simplest dynamic Bayesian network. This network allows us to design a probabilistic graphical model that can be used in machine translation field especially for sign language machine translation. In this paper, we present a Bayesian Learning based method to train the alignment between a simple GLOSS form and a more complicated GLOSS form using sign language specificities such as space locative and classifier predicates.

Keywords

Bayes methods; hidden Markov models; language translation; learning (artificial intelligence); pattern classification; sign language recognition; ASL; American Sign Language; Bayesian learning-based method; HMM-based machine translation model; alignment training; classifier predicates; complicated-GLOSS form; dynamic Bayesian network; probabilistic graphical model; sign language machine translation; sign language specificities; simple-GLOSS form; space locative; Assistive technology; Bayes methods; Fingers; Gesture recognition; Hidden Markov models; Manuals; American Sign Language GLOSS; Classifier Predicates; Dynamic Bayesian Network; HMM; Locative Space;

fLanguage

English

Publisher

ieee

Conference_Titel

Information and Communication Technology and Accessibility (ICTA), 2013 Fourth International Conference on

Conference_Location

Hammamet

Type

conf

DOI

10.1109/ICTA.2013.6815295

Filename

6815295