Soft features for statistical machine translation of spoken and signed languages
نویسنده
چکیده
Diese Dissertation ist auf den Internetseiten der Hochschulbibliothek online verfügbar. Sieh es mir nach, wenn ich weine. Acknowledgements I would like to express my deep gratitude towards Professor Hermann Ney, who granted me the possibility to, in his own words, build machines instead of pressing knobs and turning wheels. His proficiency in matters of science , his relentless search for the next step and his professionality in human interaction has been and will continue to be most inspiring. I would also like to sincerely thank co-supervisor Professor Andy Way for his kind hosting and general guidance during my stay in Dublin, as well as for his extensive feedback. I admit that he caught me a bit by surprise when he found my work truly interesting. Many thanks to Prof. Jarke, Prof. Lakemeyer and PD Unger, who in one way or the other were always there during my whole academic career and did not hesitate to support me for the viva. With profound admiration I would like to thank Davi(i)d " m-hm " Vilar for being the best Yoda I have ever had. His contribution to my structural thinking, scientific understanding and general way of programming is impossible to overestimate. Ralf Schlüter, for sharing the student's panopticon and for opening up the path to signal processing via brute-force: thank you Ralf, I owe you. Special thanks to Gregor " Aaaaah, why? " Leusch and Arne " Makakosch " Mauser for occasionaly allowing a short glimpse into their brain. A huge thank-you to Christoph " Schmitz " Schmidt for redirecting my foot steps towards a brighter future, Matthias " I lost my contact lense " Huck for helping me out in the educational stuff n' more, and to Jan " history lessons " Bungeroth for saving me from those other guys. I would also like to thank Yannick " ouuh " Gweth, Christian " nach dem Motto " Plahl and David " un-dergrads always get this wrong " Rybach for their kind administration issue solving, and of course Kai " Protoss " Frantzen and Stefan " aumix " Kolter-mann. Thanks to Evgeny " mustache " Matusov for curing me of simply v running scripts, and thanks to Richard " " Zens for his inspiring code art. Thanks to Oliver " Hast Du keine Eval? " Bender, Arnaud " looks good " Dagnelies, Thomas " Exploitation " Deselaers, Philippe " DJ " Dreuw, …
منابع مشابه
The Correlation of Machine Translation Evaluation Metrics with Human Judgement on Persian Language
Machine Translation Evaluation Metrics (MTEMs) are the central core of Machine Translation (MT) engines as they are developed based on frequent evaluation. Although MTEMs are widespread today, their validity and quality for many languages is still under question. The aim of this research study was to examine the validity and assess the quality of MTEMs from Lexical Similarity set on machine tra...
متن کاملSpoken Language Processing Techniques for Sign Language Recognition and Translation
We present an approach to automatically recognize sign language and translate it into a spoken language. A system to address these tasks is created based on state-ofthe-art techniques from statistical machine translation, speech recognition, and image processing research. Such a system is necessary for communication between deaf and hearing people. The communication is otherwise nearly impossib...
متن کاملIJCNLP 2008 Sixth SIGHAN Workshop on Chinese Language Processing
In this paper, we propose an example-based decoder for a statistical machine translation (SMT) system, which is used for spoken language machine translation. In this way, it will help to solve the re-ordering problem and other problems for spoken language MT, such as lots of omissions, idioms etc. Through experiments, we show that this approach obtains improvements over the baseline on a Chines...
متن کاملGrammar Inference and Statistical Machine Translation
NLP researchers face a dilemma: on one side, it is unarguably accepted that languages have internal structure rather than strings of words. On the other side, they nd it very di cult and expensive to write grammars that have good coverage of language structures. Statistical machine translation tries to cope with this problem by ignoring language structures and using a statistical models to depi...
متن کاملCombining Linguistics and Statistics for High-Quality Limited Domain English-Chinese Machine Translation
Second language learning is a compelling activity in today’s global markets. This thesis focuses on critical technology necessary to produce a computer spoken translation game for learning Mandarin Chinese in a relatively broad travel domain. Three main aspects are addressed: efficient Chinese parsing, high-quality English-Chinese machine translation, and how these technologies can be integrate...
متن کاملEducating the Future Workforce: Soft Skills Development in Undergraduate Translation Programs in Iran
The present study set out to investigate the concept of soft skills in academic translator education in Iran. To this aim, a needs assessment was conducted with two groups of stakeholders: i.e. translation professionals and translation students. The professionals were asked to indicate the importance of a set of soft skills in the context of the translation profession. Next, we examined through...
متن کامل