人物简历汉维机器翻译系统的设计与实现Design and implementation of Chinese-Uyghur machine translation system for personage resumes
王路路,斯拉吉艾合麦提·如则麦麦提,艾山·吾买尔,吐尔根·依布拉音,买合木提·买买提,卡哈尔江·阿比的热西提
摘要(Abstract):
为解决将汉语人物简历翻译成维吾尔语版本所面临的高成本、低效率等问题,设计并实现了一种基于模板与词典相结合的人物简历汉维机器翻译系统。通过分析汉语简历的句子结构特点,泛化命名实体并自动创建汉语的简历模板,然后利用正则表达式建立汉维模板库并结合基于规则与词典的方法翻译命名实体,以获取维吾尔语的人物简历。实验结果表明,该系统在单语的情况下使用有限的模板和词典,BLUE值可达到0.38,与需要大规模双语语料训练的机器翻译系统相比具有较好的实际应用价值。
关键词(KeyWords): 人物简历;汉维机器翻译;模板库;命名实体;正则表达式;句子结构
基金项目(Foundation): 国家“973”计划资助项目(2014CB340506);; 国家自然科学基金资助项目(61331011);国家自然科学基金资助项目(61262060);国家自然科学基金资助项目(61662077);国家自然科学基金资助项目(61462083);; 新疆多语种信息技术实验室开放课题(2016D03023);; “自治区青年科技创新人才培养工程”青年博士项目(QN2015BS004)~~
作者(Author): 王路路,斯拉吉艾合麦提·如则麦麦提,艾山·吾买尔,吐尔根·依布拉音,买合木提·买买提,卡哈尔江·阿比的热西提
DOI: 10.16652/j.issn.1004-373x.2018.24.025
参考文献(References):
- [1]林娜,唐跃勤,黎斌.谈受限汉语在机器翻译中的运用:以中文简历英译为例[J].西南交通大学学报(社会科学版),2012,13(5):49-53.LIN N,TANG Yueqin,LI Bin. Machine translation and restricted Chinese:a case study of translating Chinese resume into English[J]. Journal of Southwest Jiaotong University(Social sciences),2012,13(5):49-53.
- [2]菲利普·科恩.统计机器翻译[M].宗成庆,张霄军,译.北京:电子工业出版社,2012.KOEHN P. Statistical machine translation[M]. ZONG Chengqing,ZHANG Xiaojun,translation. Beijing:Publishing House of Electronics Industry,2012.
- [3]如克燕木·吾斯曼江,买热哈巴·艾力,吐尔根·依布拉音.基于规则的维吾尔语、哈萨克语机器翻译[J].新疆大学学报(自然科学版),2016,33(3):338-342.Rukeyanmu Wusimanjiang,Maierhaba Aili,Tuergen Yibulayin. The rule-based Uygur Kazak machine translation[J]. Journal of Xinjiang University(Natural science edition),2016,33(3):338-342.
- [4]解倩倩,艾山·吾买尔,吐尔根·依布拉音,等.混合策略的汉维辅助翻译系统的设计与实现[J].现代电子技术,2017,40(20):5-9.XIE Qianaian,Aishan Wumaier,Tuergen Yibulayin,et al. Design and implementation of Chinese and Uyghur computer-aided translation system based on hybrid strategy[J]. Modern electronics technique,2017,40(20):5-9.
- [5] ZHOU M,HUANG J X,HUANG C N,et al. Example based machine translation system:7353165[P]. 2008-04-01.
- [6]卡哈尔江·阿比的热西提.基于实例的汉维-维汉双向机器翻译系统的研究[D].上海:上海交通大学,2012.Kahaerjiang Abiderexiti. Research on an example-based Chinese-Uyghur and Uyghur-Chinese bidirectional machine translation system[D]. Shanghai:Shanghai Jiao Tong University,2012.
- [7]张冬梅,刘小蝶,晋耀红.基于模板的汉英专利机器翻译研究[J].计算机应用研究,2013,30(7):2044-2046.ZHANG Dongmei,LIU Xiaodie,JIN Yaohong. Chinese-English patent machine translation based on templates[J]. Application research of computers,2013,30(7):2044-2046.
- [8]史建国.基于模板的斯拉夫蒙古文—汉文机器翻译系统的研究与实现[D].呼和浩特:内蒙古大学,2013.SHI Jianguo. Research and implementation of Slavic MongolianChinese machine translation system based on template[D]. Hohhot:Inner Mongolia University,2013.
- [9]徐春,杨勇,董兴华.汉维/维汉统计机器翻译中若干问题研究[J].计算机工程与应用,2011,47(35):150-154.XU Chun,YANG Yong,DONG Xinghua. Research on aspects of statistical machine translation between Chinese and Uyghur[J]. Computer engineering and applications,2011,47(35):150-154.
- [10] BROWN P F,COCKE J,PIETRA S A D,et al. A statistical approach to machine translation[J]. Computational linguistics,2002,16(2):79-85.
- [11] CHO K,MERRI?NBOER B V,GULCEHRE C,et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[J/OL].[2014-09-03]. https://arxiv.org/pdf/1406.1078.pdf.
- [12] SUTSKEVER I, VINYALS O, LE Q V. Sequence to sequence learning with neural networks[J/OL].[2014-12-14].https://arxiv.org/pdf/1409.3215.pdf.
- [13] WU Y,SCHUSTER M,CHEN Z,et al. Google′s neural machine translation system:bridging the gap between human and machine translation[J/OL].[2016-10-08]. https://arxiv.org/pdf/1609.08144.pdf.