| 基于WordNet词义消歧的系统融合 |
| |
| 引用本文： | 刘宇鹏,李生,赵铁军.基于WordNet词义消歧的系统融合[J].自动化学报,2010,36(11):1575-1580. |
| |
| 作者姓名： | 刘宇鹏 李生 赵铁军 |
| |
| 作者单位： | 1.哈尔滨工业大学计算机科学与技术实验室机器翻译与智能实验室 哈尔滨 150001 |
| |
| 摘 要： | 最近混淆网络在融合多个机器翻译结果中展示很好的性能. 然而为了克服在不同的翻译系统中不同的词序, 假设对齐在混淆网络的构建上仍然是一个重要的问题. 但以往的对齐方法都没有考虑到语义信息. 本文为了更好地改进系统融合的性能, 提出了用词义消歧(Word sense disambiguation, WSD)来指导混淆网络中的对齐. 同时骨架翻译的选择也是通过计算句子间的相似度来获得的, 句子的相似性计算使用了二分图的最大匹配算法. 为了使得基于WordNet词义消歧方法融入到系统中, 本文将翻译错误率(Translation error rate, TER)算法进行了改进, 实验结果显示本方法的性能好于经典的TER算法的性能.
|
| 关 键 词： | 系统融合 翻译错误率 词义消歧 混淆网络 |
| 收稿时间： | 2009-10-13 |
| 修稿时间： | 2010-7-1 |
System Combination Based on WSD Using WordNet |
| |
| LIU Yu-Peng,LI Sheng,ZHAO Tie-Jun.System Combination Based on WSD Using WordNet[J].Acta Automatica Sinica,2010,36(11):1575-1580. |
| |
| Authors: | LIU Yu-Peng LI Sheng ZHAO Tie-Jun |
| |
| Affiliation: | 1.Machine Intelligence and Translation Laboratory, School of Computer Science and Technology, Harbin University of Technology, Harbin 150001 |
| |
| Abstract: | Recently confusion network decoding showed a better performance in combining outputs from multiple machine translation (MT) systems. However, overcoming different word orders presented in multiple MT systems during hypothesis alignment still remains to be the biggest challenge to confusion-network-based MT system combination. The previous alignment methods do not consider the information about semantics. In order to improve the system performance, we introduce word sense disambiguation (WSD) into confusion network alignment. Meanwhile, the selection of skeleton is taken through sentence similarity score, and the sentence similarity is computed by the largest bipartite graph matching algorithm. In order to combine WSD based on WordNet with our system, the experiments showed that the result using revised translation error rate (TER) algorithms is better than classic TER system combination. |
| |
| Keywords: | System combination translation error rate (TER) word sense disambiguation (WSD) confusion network (CN) |
|
| 点击此处可从《自动化学报》浏览原始摘要信息 |
|
点击此处可从《自动化学报》下载全文 |
|
