On the basis of description of the necessity in construction of the Jiangxi red tourism resource E-C/C-E bilingual parallel corpus, this paper discusses the design and construction of the corpus. In its design, it des...On the basis of description of the necessity in construction of the Jiangxi red tourism resource E-C/C-E bilingual parallel corpus, this paper discusses the design and construction of the corpus. In its design, it describes the general design and the framework of the corpus, then it describes its construction including data collection, the standard for the sorted data, data selection, data digitalization, data tagging and data aligning. With the construction, it will not only realize purposes and functions of the corpus, but also provide others with ways or means to use the corpus and to establish such kind of corpus.展开更多
The performance of a machine translation system heavily depends on the quantity and quality of the bilingual language resource. However,getting a parallel corpus,which has a large scale and is of high quality,is a ver...The performance of a machine translation system heavily depends on the quantity and quality of the bilingual language resource. However,getting a parallel corpus,which has a large scale and is of high quality,is a very difficult task especially for low resource languages such as Chinese-Vietnamese. Fortunately,multilingual user generated contents（ UGC）,such as bilingual movie subtitles,provide us access to automatic construction of the parallel corpus. Although the amount of UGC parallel corpora can be considerable,the original corpus is not suitable for statistical machine translation（ SMT） systems. The corpus may contain translation errors,sentence mismatching,free translations,etc. To improve the quality of the bilingual corpus for SMT systems,three filtering methods are proposed： sentence length difference,the semantic of sentence pairs,and machine learning. Experiments are conducted on the Chinese to Vietnamese translation corpus.Experimental results demonstrate that all the three methods effectively improve the corpus quality,and the machine translation performance（ BLEU score） can be improved by 1. 32.展开更多
文摘On the basis of description of the necessity in construction of the Jiangxi red tourism resource E-C/C-E bilingual parallel corpus, this paper discusses the design and construction of the corpus. In its design, it describes the general design and the framework of the corpus, then it describes its construction including data collection, the standard for the sorted data, data selection, data digitalization, data tagging and data aligning. With the construction, it will not only realize purposes and functions of the corpus, but also provide others with ways or means to use the corpus and to establish such kind of corpus.
基金Supported by the National Basic Research Program of China(973Program)(2013CB329303)the National Natural Science Foundation of China(61502035)
文摘The performance of a machine translation system heavily depends on the quantity and quality of the bilingual language resource. However,getting a parallel corpus,which has a large scale and is of high quality,is a very difficult task especially for low resource languages such as Chinese-Vietnamese. Fortunately,multilingual user generated contents（ UGC）,such as bilingual movie subtitles,provide us access to automatic construction of the parallel corpus. Although the amount of UGC parallel corpora can be considerable,the original corpus is not suitable for statistical machine translation（ SMT） systems. The corpus may contain translation errors,sentence mismatching,free translations,etc. To improve the quality of the bilingual corpus for SMT systems,three filtering methods are proposed： sentence length difference,the semantic of sentence pairs,and machine learning. Experiments are conducted on the Chinese to Vietnamese translation corpus.Experimental results demonstrate that all the three methods effectively improve the corpus quality,and the machine translation performance（ BLEU score） can be improved by 1. 32.
