| 基于R CN N的问题相似度计算方法 |
| |
| 引用本文： | 杨德志,柯显信,余其超,杨帮华. 基于R CN N的问题相似度计算方法[J]. 计算机工程与科学, 2021, 43(6): 1076-1080. DOI: 10.3969/j.issn.1007-130X.2021.06.017 |
| |
| 作者姓名： | 杨德志 柯显信 余其超 杨帮华 |
| |
| 作者单位： | （上海大学机电工程与自动化学院,上海 200444） |
| |
| 基金项目： | 国防基础科研计划项目（JCKY2017413C002） |
| |
| 摘 要： | 在搜索引擎、问答系统中利用深度学习的方法计算问题相似度是NLP领域研究的热点.结合卷积神经网络(CNN)和长短记忆网络(LSTM),提出了递归卷积神经网络(RCNN)问句相似度的计算方法,首先利用双向递归神经网络提取上下文信息,然后采用1D卷积神经网络将词嵌入信息与上下文信息进行融合;再利用全局最大池化提取关键信息来完...
|
| 关 键 词： | 问题相似度 递归卷积神经网络 全局最大池化 孪生网络 |
| 收稿时间： | 2019-11-15 |
| 修稿时间： | 2020-06-16 |
A question similarity calculation method based on RCNN |
| |
| YANG De-zhi,KE Xian-xin,YU Qi-chao,YANG Bang-hua. A question similarity calculation method based on RCNN[J]. Computer Engineering & Science, 2021, 43(6): 1076-1080. DOI: 10.3969/j.issn.1007-130X.2021.06.017 |
| |
| Authors: | YANG De-zhi KE Xian-xin YU Qi-chao YANG Bang-hua |
| |
| Affiliation: | （School of Mechatronic Engineering and Automation,Shanghai University,Shanghai 200444,China） |
| |
| Abstract: | Using deep learning to calculate the question similarity in search engine and question answering system is a hotspot in the NLP field. Combining convolutional neural network (CNN) and long-short memory network (LSTM), a recursive convolutional neural network (RCNN) question similarity calculation method is proposed. Firstly, the bidirectional recursive neural network is utilized to extract context information,and then the 1D Convolutional Neural Network was used to integrate the word embedded information with the context information. Then the global maximum pooling is used to extract the key information to complete the semantic representation of the two questions.Finally, the similarity of the question pair is judged through the matching layer. The experimental results show that, based on the Quora Question Pairs data set, the accuracy of the question similarity calculation method is 83.57%, which is better than other methods. |
| |
| Keywords: | question similarity recursive convolutional neural network global maximum pooling siamese network |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与科学》浏览原始摘要信息 |
|
点击此处可从《计算机工程与科学》下载全文 |
|
