{"id":118,"date":"2017-05-18T04:22:01","date_gmt":"2017-05-18T04:22:01","guid":{"rendered":"http:\/\/achrafothman.net\/site\/?p=118"},"modified":"2021-10-18T03:56:04","modified_gmt":"2021-10-18T03:56:04","slug":"phd-defense","status":"publish","type":"post","link":"https:\/\/achrafothman.net\/site\/phd-defense\/","title":{"rendered":"PhD Defense: \u201cMachine Translation for Sign Language based on Statistical Approach\u201c"},"content":{"rendered":"

I am happy to report that on March\u00a010, 2017, I had my doctoral dissertation defense, as part of the WebSign project<\/a>, and that the committee found my research to be worthy. My dissertation was titled \u201cMachine Translation for Sign Language based on Statistical Approach\u201d<\/em> and was based on translation between American Sign Language and English written text, as well as new transcription system for Sign Language based on Gloss Annotation System was proposed.<\/p>\n

The defense was intense, but I got a ton of useful questions and comments, and already have new ideas pinging in my brain about where to take this research next. I am thankful to my committee members: Prof. Mohamed Jemni, Prof. Faiez Gargouri, Prof. Chiraz Latiri, Prof. Mounir Zrigui and, Prof. Kais Haddar.<\/p>\n

 <\/p>\n

Abstract :<\/strong><\/p>\n

In this thesis, we deal with machine translation to sign language. We start with studying existing systems and issues in order to propose a new model for statistical machine translation from written english text to American Sign Language (English\/ASL). Indeed, we proposed a new approach aiming to build artificial corpus using grammatical dependencies rules. The parallel corpus was the input of our machine translation that has been used to create the statistical memory translation based on the IBM alignment algorithms. These algorithms have been improved and optimized by integrating Jaro-Winkler distances. Then, based on the constructed translation memory, we have modeled and implemented a decoder to translate an English text to the American sign language using a new transcription system based on gloss annotation. The obtained results were evaluated by the BLEU evaluation metric used in the field of machine translation.<\/p>\n

 <\/p>\n

If you\u2019re just writing\u00a0about\u00a0my work, please cite this thesis\u00a0as follow:<\/p>\n

Achraf Othman, “Machine Translation for Sign Language based on Statistical Approach<\/em><\/a>“, PhD Thesis, University of Sfax, Tunisia, (2017).<\/strong><\/p>\n

 <\/p>\n

 <\/p>\n

Phd Presentation (in French):
\n