A study on machine translation for low resource languages
➤ Gửi thông báo lỗi ⚠️ Báo cáo tài liệu vi phạmNội dung chi tiết: A study on machine translation for low resource languages
A study on machine translation for low resource languages
A STUDY ON MACHINE TRANSLATION FOR LOW-RESOURCE LANGUAGESBy TRIEU, LONG HAIsubmitted toJapan Advanced Institute of Science and Technology, in partial A study on machine translation for low resource languages fulfillment of the requirements for the degree ofDoctor of PhilosophyWritten under the direction ofAssociate Professor Nguyen Minh LeSeptember, 2017A STUDY ON MACHINE TRANSLATION FOR LOW-RESOURCE LANGUAGESBy TRIEIỊ LONG HAI (1420211)A thesis submitted to School of Information Science, Japan Advance A study on machine translation for low resource languages d Institute of Science and Technology, in partial fulfillment of the requirements for the degree of Doctor of Information ScienceGraduate Program in IA study on machine translation for low resource languages
nformation ScienceWritten under the direction of Associate Professor Nguyen Minh Leand approved by Associate Professor Nguyen Minh Le Professor SatoshA STUDY ON MACHINE TRANSLATION FOR LOW-RESOURCE LANGUAGESBy TRIEU, LONG HAIsubmitted toJapan Advanced Institute of Science and Technology, in partial A study on machine translation for low resource languages G HAIAcknowledgementsAbstractCurrent state-of-the-art machine translation methods are neural machine translation and statistical machine translation, which based on translated texts (bilingual corpora) to learn t ranslation rules automatically. Nevertheless, large bilingual corpora are unavailable f A study on machine translation for low resource languages or most languages in the world, called low-resource languages, that, cause a bottleneck for machine translation (MT). Therefore, improving MT on low-rA study on machine translation for low resource languages
esource languages becomes one of the essential tasks in MT currently.In this dissertation. 1 present my proposed methods to improve MT on low-resourceA STUDY ON MACHINE TRANSLATION FOR LOW-RESOURCE LANGUAGESBy TRIEU, LONG HAIsubmitted toJapan Advanced Institute of Science and Technology, in partial A study on machine translation for low resource languages vot methods. For the first strategy, I proposed a met hod to improve sentence alignment based on word similarity learnt, from monolingual data to build bilingual corpora. Then, a multilingual parallel corpus was built using the proposed method to improve MT on several Southeast Asian low-resource la A study on machine translation for low resource languages nguages. Experimental results showed the effectiveness of the proposed alignment method to improve sentence alignment and (he contribution of the extrA study on machine translation for low resource languages
acted corpus to improve MT performance. For the second strategy, I proposed two methods based on semant ic similarity and using grammat ical and morphA STUDY ON MACHINE TRANSLATION FOR LOW-RESOURCE LANGUAGESBy TRIEU, LONG HAIsubmitted toJapan Advanced Institute of Science and Technology, in partial A study on machine translation for low resource languages source-pivot and pivot-t arget bilingual corpora. I conducted experiments on low-resource language pairs such as t he translation from Japanese, Malay, Indonesian, and Filipino to Vietnamese and achieved promising results and improvement. Additionally, a hybrid model was introduced that combines t A study on machine translation for low resource languages he t wo st rategies to further exploit additional data to improve MT performance. Experiments were conducted on several language pairs: Japanese-VietnA study on machine translation for low resource languages
amese, Indonesian-Vietnamese, Malay-Vietnamese, and Turkish-English, and achieved a significant improvement. In addition, I utilized and investigated A STUDY ON MACHINE TRANSLATION FOR LOW-RESOURCE LANGUAGESBy TRIEU, LONG HAIsubmitted toJapan Advanced Institute of Science and Technology, in partial A study on machine translation for low resource languages ompared NMT with phrase-based methods on low-resource settings, and investigated how the low-resource data affects the two methods. The results are useful for further development of NMT on low-resource languages. I conclude with how my work contributes to current MT research especially for low-resou A study on machine translation for low resource languages rce languages and enhances t he development of MT on such languages in the future.Keywords: machine translation, phrase-based machine translation, neuA study on machine translation for low resource languages
ral-based machine translation, low-resource languages, bilingual corpora, pivot translation, sentence alignment9AcknowledgementsFor three years workinA STUDY ON MACHINE TRANSLATION FOR LOW-RESOURCE LANGUAGESBy TRIEU, LONG HAIsubmitted toJapan Advanced Institute of Science and Technology, in partial A study on machine translation for low resource languages t, wit h. This work gives me a lot of interest ing knowledge and experiences as well as difficulties that require me with the best efforts. At the moment of writing this dissert ation as a summary for the PhD journey, it reminds me a lot. of support from many people. This work cannot, be completed w A study on machine translation for low resource languages ithout their support.First of all, 1 would like to thank my supervisor. Associate Professor Nguyen Minh Le. Professor Nguyen gives mo a lot. of commenA study on machine translation for low resource languages
ts, advices, discussions in my whole three-year journey from the starting point when I approached this topic without any prior knowledge about, machinA STUDY ON MACHINE TRANSLATION FOR LOW-RESOURCE LANGUAGESBy TRIEU, LONG HAIsubmitted toJapan Advanced Institute of Science and Technology, in partial A study on machine translation for low resource languages so one of the most, challenge things for everyone in the academic career. Thanks to the useful and interesting discussions with professor Nguyen, I have overcome the most difficult periods in doing this research. Not only leach me some first lessons and skills in doing research, professor Nguyen als A study on machine translation for low resource languages o has interesting and useful discussions that, help me a lot in both studying and the life.1 would like to (hank the committee: Professor Satoshi TojoA study on machine translation for low resource languages
, Professor Hiroyuki lida, Associate Professor Ittoo Ashwin, Associate Professor Kiyoaki Shirai for their comments. This can Im one of t he first workA STUDY ON MACHINE TRANSLATION FOR LOW-RESOURCE LANGUAGESBy TRIEU, LONG HAIsubmitted toJapan Advanced Institute of Science and Technology, in partial A study on machine translation for low resource languages aluable comments, they help me a lot in improving this dissertation.1 also would like to thank my collaborators: Associate Professor Nguyen Phuong Thai for his comments, advices, and experience in sentence alignment and machine translat ion. 1 would like to t hank Vu Tran, Tin Pham, Viet-Anh Phan fo A study on machine translation for low resource languages r their int erest ing discussions and collaborations ill doing some topics in this research. Thanks so much to Vu Tran, Chien Tran for their technicalA study on machine translation for low resource languages
support.1 would like to thank my colleagues and friends, Truong Nguyen, Huy Nguyen, for their support, and encourage. I also would like to give a speA STUDY ON MACHINE TRANSLATION FOR LOW-RESOURCE LANGUAGESBy TRIEU, LONG HAIsubmitted toJapan Advanced Institute of Science and Technology, in partial A study on machine translation for low resource languages ecial thank to professor Ho Tu Bao for valuable advices in research. Thanks so much to Danilo s. Carvalho, Tien Nguyen for t heir comments.Last but not least, I would like to thank my parents, Till Trieu, Phuong Hoang, my sister Ly Tricu. and my wife Xuan Dam for their support and encouragement in a A study on machine translation for low resource languages ll t ime not only in t his work but. in my life.3IA STUDY ON MACHINE TRANSLATION FOR LOW-RESOURCE LANGUAGESBy TRIEU, LONG HAIsubmitted toJapan Advanced Institute of Science and Technology, in partial A STUDY ON MACHINE TRANSLATION FOR LOW-RESOURCE LANGUAGESBy TRIEU, LONG HAIsubmitted toJapan Advanced Institute of Science and Technology, in partialGọi ngay
Chat zalo
Facebook