级联中文组块识别  

Cascade Identification of Chinese Chunks

作　　者：秦颖[1] 王小捷[1] 钟义信[1] 

机构地区：[1]北京邮电大学信息工程学院,北京100876

出　　处：《北京邮电大学学报》2008年第1期14-17,共4页Journal of Beijing University of Posts and Telecommunications

基　　金：语言司民文语科库工具建设项目(MZ115-022)

摘　　要：基于统计方法的中文组块研究大多借鉴CoNLL2000英文组块的思想,建立了组块表示的BIO模型,并将组块识别任务作为一种为词序列标注的多分类问题.为降低分类复杂度,采取了一种分解识别法,即先识别组块的边界,再进行组块类别判定.基于条件随机场(CRF)构建了级联组块识别器,实验数据集采用宾州大学中文树库(CTB5.1).在特征选择上,借鉴了中文分词特征选择的方法.5倍交叉验证的实验结果为:组块边界识别的F1值为95.05%;类型识别的准确率为99.43%;整体F1值为93.58%.该方法提高了系统性能,缩短了学习器的训练时间.Most statistical-based Chinese chunking researches was inspired by English chunking of CoNLL2000. After representing chunks within the scheme of tags for words in a chunk, chunk identification task was cast as word sequence tagging and tackled as multi-classification problems. For sake of decreasing classification complexity, a decomposed chunking approach was proposed： first, chunk boundary identification, and then chunk type identification. The vital problem of Chinese chunking is actually boundary identification. Cascade chunk identifiers were built based on conditional random fields （CRF）. The experimental dataset was extracted from Chinese tree bank 5.1 （CTBS. 1）. As to the features selection, some methods often used in Chinese word segmentation were borrowed to chunking task. On 5 cross validation of dataset, F1-measure of chunk boundary identification is 95.05 %, and the precision of chunk type recognition is 99.43 % as well. And the total chunking F1- meausre reaches 93.58 %. Comparing with other relative researches, the performance is improved and the training time of learners is sharply shortened.

关 键 词：中文组块 边界识别 类别识别 条件随机场 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]