节点文献
面向多领域资源的汉英双语语料库构建的研究
Study on Chinese-English corpus construction toward multiple-domain resources
【摘要】 针对Web上双语资源的多领域性和布局规律性,提出一种拟合多领域特征和位置特征的概率对齐模型。该方法同目前对齐模型相比,在对齐准确率和召回率上分别提高了37%和40.4%。
【Abstract】 With the consideration of the features of open, multiple-domain and layout regularity of bilingual resources on Web, a mixture probabilistic alignment model was proposed to reveal the domain-specific and position-specific characteristic for aligning texts. Compared to the traditional lengthen-based aligning model, the model in this paper achieves 37% and 40.4% improvement on precise and recall respectively with the extensive experiments.
【关键词】 统计概率对齐;
混合模型;
多领域;
【Key words】 statistic probabilistic alignment; mixture probability model; multiple-domain;
【Key words】 statistic probabilistic alignment; mixture probability model; multiple-domain;
【基金】 国家自然科学基金资助项目(60703068;60573090)
- 【文献出处】 计算机应用 ,Journal of Computer Applications , 编辑部邮箱 ,2008年01期
- 【分类号】TP391.1
- 【被引频次】7
- 【下载频次】353