Investigation and Use of Methods for Defining the Extends of Similarity of Kazakh Language Sentences推荐.pdf

Investigation and Use of Methods for Defining the Extends of Similarity of Kazakh Language Sentences Unzila Kamanur1(), Altynbek Sharipbay1(), Gulila Altenbek2(), Gulmira Bekmanova1, and Lena Zhetkenbay1 1 L.N. Gumilyov Eurasian National University, Astana, Kazakhstan {unzila.88,sharalt,jetlen_7}@mail.ru, gulmira-r@yandex.ru 2 Xinjiang University, Urumqi, China glaxd2014@163.com Abstract. Finding similarity degree is one of the significant technologies used in the sample-based machine translation. It works in the following principle, first matching the input sentences with a sentence in the sample database, after that it is necessary to pick up parts of the similar sentences for the sentence which is aimed to translate; it is finished by correcting the structure or paraphrasing it with a relevant meaning. For that reason, the degree of similarity of two samples highly affects on the results of translation. Thus, there are dependence between quality of the outputs and the similarity degree. Keywords: EBMT Synonym replacement Kazakh sentence Similarity sentence similarity Machine translation Natural language processing 1 Introduction The translation from one language to another is considered that it was introduced as a separate science for the first time in 1947 in the letter written by Warren Wiver for Nobert Viner [ 1]. After that, it can be seen that in the last 50 years the quick devel- opment of this study has occurred. Nowadays, a number of machine translation tools became available for users, various types of machine translation systems are widely used al