《計算機應用研究》|Application Research of Computers

基于MAC-LSTM的問題分類研究

Question classification based on MAC-LSTM

免費全文下載 (已被下載 次)  
獲取PDF全文
作者 余本功,許慶堂,張培行
機構 合肥工業大學 a.管理學院;b.過程優化與智能決策教育部重點實驗室,合肥 230009
統計 摘要被查看 次,已被下載
文章編號 1001-3695(2020)01-008-0040-04
DOI 10.19734/j.issn.1001-3695.2018.05.0452
摘要 針對問句文本通常較短、語義信息與詞語共現信息不足等問題,提出一種多層級注意力卷積長短時記憶模型(multi-level attention convolution LSTM neural network,MAC-LSTM)的問題分類方法。相比基于詞嵌入的深度學習模型,該方法使用疑問詞注意力機制對問句中的疑問詞特征重點關注。同時,使用注意力機制結合卷積神經網絡與長短時記憶模型各自文本建模的優勢,既能夠并行方式提取詞匯級特征,又能夠學習更高級別的長距離依賴特征。實驗表明,該方法較傳統的機器學習方法和普通的卷積神經網絡、長短時記憶模型有明顯的效果提升。
關鍵詞 問答系統; 問題分類; 注意力機制; 疑問詞注意力機制; 卷積神經網絡; 長短時記憶模型
基金項目 國家自然科學基金資助項目(71671057)
本文URL http://www.048285.live/article/01-2020-01-008.html
英文標題 Question classification based on MAC-LSTM
作者英文名 Yu Bengong, Xu Qingtang, Zhang Peihang
機構英文名 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.
英文關鍵詞 question and answering; question classification; attention mechanism; interrogative attention mechanism; convolutional neural networks; LSTM
參考文獻 查看稿件參考文獻
 
收稿日期 2018/5/21
修回日期 2018/7/12
頁碼 40-43
中圖分類號 TP391
文獻標志碼 A
012曾道人三尾中特书