200_利用adaboost-svm集成算法和语块信息的韵律短语识别.pdf

文章编号：1003-0077 （2015）00-0000-00 利用AdaBoost-SVM 集成算法和语块信息的韵律短语识别 1,2 1 钱揖丽 ，冯志茹 (1. 山西大学 计算机与信息技术学院，山西 太原 030006 ； 2. 山西大学 计算智能与中文信息处理教育部重点实验室，山西 太原 030006) 摘要：该文提出一种基于汉语语块结构并利用AdaBoost-SVM 集成学习算法的汉语韵律短语识别方法。首 先，对语料进行自动分词、词性标注和初语块标注，然后利用基于结合紧密度获取的规则对初语块进行归 并，得到最终的语块结构。其次，基于语块结构并利用AdaBoost-SVM 集成算法，构建汉语韵律短语识别 模型。同时，该文利用多种算法分别构建了利用语块信息和不利用语块的多个模型，对比实验结果表明， 表示浅层句法信息的语块能够在韵律短语识别中做出积极有效的贡献；利用 AdaBoos-SVM 集成算法实现 的模型性能更佳。 关键词：汉语语块；AdaBoost-SVM；韵律短语；识别 中图分类号：TP391 文献标识码：A Recognition of Chinese prosodic phrase based on AdaBoost-SVM algorithm and chunk information QIAN Yili1,2 , FENG Zhiru1 (1. School of Computer Information Technology, Shanxi University, Taiyuan, Shanxi 030006, China; 2. Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, Shanxi University, Taiyuan, Shanxi 030006, China) Abstract: A method for Chinese prosodic phrase recognition based on Chunk and AdaBoost-SVM algorithm is proposed in this paper. Firstly, the initial chunks are marked on the corpus of automatic word segmentation and part of speech tagging, and then they are merged using the rules based on the closeness between initial Chunks. Secondly, based on the block structure and the AdaBoost-SVM integrated algorithm, a Chinese prosodic phrase recognition model is constructed. Meanwhile this paper utilized various algorithms to build different models which use or not use Chunk information, the comparative experimental results show that the shallow syntactic information Chunk has made a positive and effective contribution to Chinese prosodic phrase recognition, and the performance of the AdaBoost-SVM model is better. Key words: Chinese chunk; AdaBoost-SVM; prosodic phrase; recognition 1 引言 语音合成是