Investigation and use of methods for defining the extends of similarity of Kazakh language sentences

摘要：

　　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.

关键词： EBMT Synonym replacement Kazakh sentence similarity sentence similarity machine translation natural language processing

作者: Unzila Kamanur Altynbek Sharipbay Gulila Altnbek Gulmira Bekmanova Lena Zhetkenbay

作者单位: L.N.Gumilyov Eurasian National University,Astana

会议类型: 国内会议

会议名称: 第十五届全国计算语言学学术会议(CCL2016)暨第四届基于自然标注大数据的自然语言处理国际学术研讨会(NLP-NABD-2016)

会议地点: 烟台

会议语种:英文

页码: 1-9

在线出版日期: 2016-10-14（万方平台首次上网日期，不代表论文的发表时间）