CAJ | 학술논문

DBN是一种快速全局最优的神经网络分类方法，包含数层无监督学习网络和一层有监督学习网络。本文验证了DBN方法很好地适用于中文名实体分类任务。首先，采用多层RBM方法无监督地从字特征向量提取结构信息，得到更具有表征能力的特征；然后，利用BP方法微调网络参数并对提取后的特征向量进行分类，以此构成分类器进行名实体分类。通过对 ACE 04的中文名实体进行的分类测试，准确率达到91．45％，明显高于支持向量机和反向传播神经网络等传统分类算法。
DBN시일충쾌속전국최우적신경망락분류방법，포함수층무감독학습망락화일층유감독학습망락。본문험증료DBN방법흔호지괄용우중문명실체분류임무。수선，채용다층RBM방법무감독지종자특정향량제취결구신식，득도경구유표정능력적특정；연후，이용BP방법미조망락삼수병대제취후적특정향량진행분류，이차구성분류기진행명실체분류。통과대 ACE 04적중문명실체진행적분류측시，준학솔체도91．45％，명현고우지지향량궤화반향전파신경망락등전통분류산법。
DBN is a classification of fast and global optimum neural network .It contains several layers of unsupervised net-works and one layer of supervised network .The paper approves this novelty machine learning approach is suitable to the do -main of named entity categorization .The paper applies RBM ,an unsupervised learning method , to reconstruct more repre-sentative features from character-based features .Subsequently , the paper utilizes BP , a supervised learning method , to fine-tune parameters in whole network and accomplish the categorization task .In the end, the paper tests DBN on ACE 04 Chinese corpus and achieve 91.45%precision, which is much better than Support Vector Machine and Back-propagation neural network .