基于深度学习的问题分类方法研究  

Research on Problem Classification Method Based on Deep Learning

作　　者：李超[1] 柴玉梅[1] 南晓斐[1] 高明磊[1] 

机构地区：[1]郑州大学信息工程学院,郑州450001

出　　处：《计算机科学》2016年第12期115-119,共5页Computer Science

摘　　要：问题分类是问答系统中的重要组成部分。但现阶段的问题分类需要人工制定提取特征的策略和不断优化特征规则。深度学习方法在问题分类上具有可行性,通过自我学习特征的方式表示和理解问题,避免人工特征的制定,从而减少人工代价。针对问题分类,改进了长短期记忆人工神经网络(LSTM)和卷积神经网络(CNN)模型,并结合两者的优势组合成为一种新的学习框架(LSTM-MFCNN),加强对词序语义和深度特征的学习。实验结果表明,该方法在不需要制定繁琐的特征规则的条件下,仍然有较好的表现,准确率达到了93.08%。Question classification is an important part of question answering system. But question classification requires the strategy of extracting features and the continuous optimization of characteristic rules at the present stage. The method of deep learning is feasible in the question classification by the way of self learning question characteristics to represent and understand the problem so as to avoid formulating artificial features and reduce labor costs. For question classifica- tion, the long-short term memory（LSTM） model and the convolution neural network （CNN） model were improved, combining the advantages of these two models into a new learning framework （LSTM-MFCNN） to strengthen the semantic study of word order and study of depth characteristics. Experimental results show that the proposed method still has good performance under the condition of no need to formulate the characteristic rules, and the accuracy of this method is 93. 08%.

关 键 词：问题分类 深度学习 卷积神经网络 LSTM 机器学习 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]