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

基于GRU和注意力機制的遠程監督關系抽取

Distant supervision relationship extraction based on GRU and attention mechanism

免費全文下載 (已被下載 次)  
獲取PDF全文
作者 黃兆瑋,常亮,賓辰忠,孫彥鵬,孫磊
機構 桂林電子科技大學 廣西可信軟件重點實驗室,廣西 桂林 541004
統計 摘要被查看 次,已被下載
文章編號 1001-3695(2019)10-010-2930-04
DOI 10.19734/j.issn.1001-3695.2018.03.0197
摘要 隨著深度學習的發展,越來越多的深度學習模型被運用到了關系提取的任務中,但是傳統的深度學習模型無法解決長距離依賴問題;同時,遠程監督將會不可避免地產生錯誤標簽。針對以上兩個問題,提出一種基于GRU(gated recurrent unit)和注意力機制的遠程監督關系抽取方法。首先通過使用GRU神經網絡來提取文本特征,解決長距離依賴問題;接著在實體對上構建句子級的注意力機制,減小噪聲句子的權重;最后在真實的數據集上,通過計算準確率、召回率并繪出PR曲線證明該方法與現有的一些方法相比,取得了比較顯著的進步。
關鍵詞 深度學習; 遠程監督; 門控循環單元; 注意力機制
基金項目 國家自然科學基金資助項目(U1501252,61572146)
廣西創新驅動重大專項項目(AA17202024)
廣西自然科學基金資助項目(2016GXNSFDA380006)
廣西信息科學實驗中心平臺建設項目(PT1601)
本文URL http://www.pbxovf.icu/article/01-2019-10-010.html
英文標題 Distant supervision relationship extraction based on GRU and attention mechanism
作者英文名 Huang Zhaowei, Chang Liang, Bin Chenzhong, Sun Yanpeng, Sun Lei
機構英文名 Guangxi Key Laboratory of Trusted Software,Guilin University of Electronic Technology,Guilin Guangxi 541004,China
英文摘要 With the development of deep learning, more and more deep learning models have been applied to the task of relation extraction, but traditional deep learning models can't solve long distance dependence problems. At the same time, distant supervision will inevitably generate wrong labels. For these two problems, this paper proposed a distant supervision relationship extraction method based on GRU(gated recurrent unit) and the attention mechanism. First, it adopted the GRU neural network to extract text features and solve long-distance dependence problems. Second, it constructed a sentence-level attention mechanism on entity pairs to reduce the weight of noise sentences. Finally, based on the real data set, by calculating the accuracy rate and recall rate, and drawing the PR curve to prove the proposed method has achieved significant progress compared with some existing methods.
英文關鍵詞 deep learning; distant supervision; GRU; attention mechanism
參考文獻 查看稿件參考文獻
 
收稿日期 2018/3/19
修回日期 2018/4/28
頁碼 2930-2933
中圖分類號 TP391
文獻標志碼 A
黑龙江时时玩法介绍