發(fā)布時間：2018-04-16 22:41

  本文選題：事件識別 + 深度學(xué)習(xí)��； 參考：《電子學(xué)報》2017年06期

【摘要】：事件識別是信息抽取的重要基礎(chǔ).為了克服現(xiàn)有事件識別方法的缺陷,本文提出一種基于深度學(xué)習(xí)的事件識別模型.首先,我們通過分詞系統(tǒng)獲得候選詞并將它們分為五種類型.然后選擇六種識別特征并制定相應(yīng)的特征表示規(guī)則用來將詞轉(zhuǎn)化為向量樣例.最后我們通過深度信念網(wǎng)絡(luò)抽取詞的深層語義信息,并由Back-Propagation(BP)神經(jīng)網(wǎng)絡(luò)識別事件.實驗顯示模型最高F值達(dá)85.17%.同時,本文還提出了一種融合無監(jiān)督和有監(jiān)督兩種學(xué)習(xí)方式的混合監(jiān)督深度信念網(wǎng)絡(luò),該網(wǎng)絡(luò)能夠提高識別效果(F值達(dá)89.2%)并控制訓(xùn)練時間(增加27.50%).
[Abstract]:Event recognition is an important basis for information extraction.In order to overcome the shortcomings of existing event recognition methods, this paper presents an event recognition model based on deep learning.First, we obtain candidate words through word segmentation system and divide them into five types.Then six recognition features are selected and corresponding feature representation rules are made to transform words into vector samples.Finally, the deep semantic information of words is extracted by deep belief network, and the event is identified by Back-Propagation BP neural network.The experiment shows that the maximum F value of the model is 85.17.At the same time, this paper proposes a hybrid supervised depth belief network which combines unsupervised and supervised learning methods. The network can improve the recognition effect and control the training time (increase 27.50%).
【作者單位】： 上海大學(xué)計算機工程與科學(xué)學(xué)院;
【基金】：國家自然科學(xué)基金項目(No.61273328,No.61305053,No.71203135)
【分類號】：TP18;TP391.1
，

本文編號：1760922