《计算机应用研究》|Application Research of Computers

基于MAC-LSTM的问题分类研究

Question classification based on MAC-LSTM

免费全文下载 (已被下载 次)  
获取PDF全文
作者 余本功,许庆堂,张培行
机构 合肥工业大学 a.管理学院;b.过程优化与智能决策教育部重点实验室,合肥 230009
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2020)01-008-0040-04
DOI 10.19734/j.issn.1001-3695.2018.05.0452
摘要 针对问句文本通常较短、语义信息与词语共现信息不足等问题,提出一种多层级注意力卷积长短时记忆模型(multi-level attention convolution LSTM neural network,MAC-LSTM)的问题分类方法。相比基于词嵌入的深度学习模型,该方法使用疑问词注意力机制对问句中的疑问词特征重点关注。同时,使用注意力机制结合卷积神经网络与长短时记忆模型各自文本建模的优势,既能够并行方式提取词汇级特征,又能够学习更高级别的长距离依赖特征。实验表明,该方法较传统的机器学习方法和普通的卷积神经网络、长短时记忆模型有明显的效果提升。
关键词 问答系统; 问题分类; 注意力机制; 疑问词注意力机制; 卷积神经网络; 长短时记忆模型
基金项目 国家自然科学基金资助项目(71671057)
本文URL http://www.arocmag.com/article/01-2020-01-008.html
英文标题 Question classification based on MAC-LSTM
作者英文名 Yu Bengong, Xu Qingtang, Zhang Peihang
机构英文名 a.School of Management,b.Key Laboratory of Process Optimization & Intelligent Decision-making of Ministry of Education,Hefei University of Technology,Hefei 230009,China
英文摘要 Question text is usually short and the information of semantic information and word co-occurrence are not enough. To address the above problems, this paper proposed a multi-level attention convolution LSTM neural network(MAC-LSTM) for question classification. This approach used the interrogative word attention mechanism to focus on the interrogative features in the heterogeneous question contexts. At the same time, it used the attention mechanism combined with the advantages of convolutional neural network and long-short memory model recurrent neural network(LSTM). MAC-LSTM is able to capture both local features of phrases as well as global and temporal sentence semantics. Experiments show that, this approach achieves better performance than traditional machine learning method, ordinary convolutional neural network, and traditional LSTM on question classification tasks without the need of prior knowledge.
英文关键词 question and answering; question classification; attention mechanism; interrogative attention mechanism; convolutional neural networks; LSTM
参考文献 查看稿件参考文献
 
收稿日期 2018/5/21
修回日期 2018/7/12
页码 40-43
中图分类号 TP391
文献标志码 A