|
|||||
|
|
| 引入集成学习的最大熵短语调序模型 | |
| 引用本文： | 何钟豪,苏劲松,史晓东,陈毅东,黄研洲. 引入集成学习的最大熵短语调序模型[J]. 中文信息学报, 2014, 28(1): 87-93 |
| 作者姓名： | 何钟豪 苏劲松 史晓东 陈毅东 黄研洲 |
| 作者单位： | 1. 厦门大学 智能科学与技术系, 福建 厦门 361005; 2. 厦门大学 软件学院, 福建 厦门 361005 |
| 基金项目： | 国家自然科学基金(61303082,61005052);国家科技支撑计划(2012BAH14F03);高等学校博士学科点专项科研基金(20120121120046) |
| 摘 要： | 基于最大熵的括号转录语法模型具有翻译能力强、模型训练简单的优点,成为近些年统计机器翻译研究的热点。然而,该模型存在短语调序实例样本分布不平衡的缺点。针对该问题,该文提出了一种引入集成学习的短语调序模型训练方法。在大规模数据集上的实验结果表明,我们的方法能有效改善调序模型的训练效果,显著提高翻译系统性能。 |
| 关 键 词： | 最大熵 短语调序 不平衡分类 集成学习 |
An Ensemble Learning Method for Maximum Entropy Based Phrase Reordering Model |
|
| HE Zhonghao,SU Jinsong,SHI Xiaodong,CHEN Yidong,HUANG Yanzhou. An Ensemble Learning Method for Maximum Entropy Based Phrase Reordering Model[J]. Journal of Chinese Information Processing, 2014, 28(1): 87-93 | |
| Authors: | HE Zhonghao SU Jinsong SHI Xiaodong CHEN Yidong HUANG Yanzhou |
| Affiliation: | 1. Cognitive Science Department, Xiamen University, Xiamen, Fujian 361005, China; 2. Software School, Xiamen University, Xiamen, Fujian 361005, China |
| Abstract: | The Maximum Entropy Based BTG model becomes a hot topic in statistical machine translation in recent years due to its strong translation and easy-to-train abilities. However, the distribution of reordering examples in this model is imbalanced. To solve this problem, we introduce an ensemble learning method for training phrase reordering model. Experimental results show that,the reordering model can reach a better training effect via our method and the performance of the translation system is improved significantly in a large-scale dataset. |
| Keywords: | maximum entropy phrase reordering imbalanced classifier ensemble learning |
| 本文献已被 CNKI 等数据库收录！ | |
| 点击此处可从《中文信息学报》浏览原始摘要信息 | |
| 点击此处可从《中文信息学报》下载全文 | |