| 英汉专利语料中长句的分割 |
| |
| 引用本文： | 张西龙,季铎,王岩,苗雪雷.英汉专利语料中长句的分割[J].沈阳航空工业学院学报,2011,28(5):67-70. |
| |
| 作者姓名： | 张西龙 季铎 王岩 苗雪雷 |
| |
| 作者单位： | 沈阳航空航天大学知识工程中心,辽宁沈阳,110136 |
| |
| 摘 要： | 平行语是基于语料机器翻译方法的重要资源。专利语料中存在大量长句，这给机器翻译系统学习翻译模型带来了复杂性。因此，对专利语料中长句的分割将是十分有必要的。提出了一种基于统计词对齐的专利语料中长句分割方法，将标点的对应位置作为候选分割位置有效的保留了句子的句法结构，并且使用改进后的IBM翻译模型1对分割片段进行评分，进一步保证了长句分割的正确性。翻译实验证明该方法有效地提高了翻译系统的质量。
|
| 关 键 词： | 句子分割 专利语料 统计对齐 翻译模型 |
On long sentence segmentation for C-E parallel patent corpora |
| |
| ZHANG Xi-long,JI Duo,WANG Yan,MIAO Xue-lei.On long sentence segmentation for C-E parallel patent corpora[J].Journal of Shenyang Institute of Aeronautical Engineering,2011,28(5):67-70. |
| |
| Authors: | ZHANG Xi-long JI Duo WANG Yan MIAO Xue-lei |
| |
| Institution: | ZHANG Xi-long,JI Duo,WANG Yan,MIAO Xue-lei(Knowledge Engineering Research Center,Shenyang Aerospace University,Liaoning Shenyang 110136) |
| |
| Abstract: | Parallel corpora have proved extremely useful resources for the corpus-based machine translation.It is of great necessity to segment long sentences in Chinese-English parallel patent corpora to make it easy to use translation models in corpus-based machine translation systems.This paper puts forward a new statistical alignment method of long sentence segmentation,i.e.treating positions of punctuations as candidate split points,and then evaluates the segments by modified IBM model 1 which makes sentence segm... |
| |
| Keywords: | sentence segmentation patent corpus statistical alignment translation model |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
