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

基于自注意力機制的方面情感分類

Aspect-level sentiment classification based on self-attention mechanism

免費全文下載 (已被下載 次)  
獲取PDF全文
作者 王拂林,劉丹,昌茜
機構 電子科技大學 電子科學技術研究院,成都 611731
統計 摘要被查看 次,已被下載
文章編號 1001-3695(2020)11-005-3227-05
DOI 10.19734/j.issn.1001-3695.2019.07.0259
摘要 基于方面的情感分類方法判斷句子中給定實體或屬性的情感極性。針對使用全局注意力機制計算屬性詞和句子其他詞的注意力分數時,會導致模型關注到與屬性詞不相關的詞,并且對于長距離的依賴詞、否定詞關注不足,不能檢測到并列關系和短語的問題,提出了基于自注意力機制的語義加強模型(SRSAM)。該模型首先使用雙向長短時記憶神經網絡模型(bidirectional long short-term memory,BiLSTM)獲取文本編碼,其次用自注意力機制計算文本編碼的多個語義編碼,最后將屬性詞和語義編碼交互后判斷屬性詞在句中的情感極性。使用SemEval 2014數據集的實驗表明,由于模型能發現長距離依賴和否定詞,對并列關系和短語有一定檢測效果,相比基礎模型在分類精度上有0.6%~1.5%的提升。
關鍵詞 方面詞; 情感分類; 自注意力機制; 語義編碼
基金項目
本文URL http://www.gvztwvrl.buzz/article/01-2020-11-005.html
英文標題 Aspect-level sentiment classification based on self-attention mechanism
作者英文名 Wang Fulin, Liu Dan, Chang Xi
機構英文名 Research Institute of Electronic Science & Technology,University of Electronic Science & Technology of China,Chengdu 611731,China
英文摘要 Aspect-level sentiment classification determines the emotional polarity from sentence towards a specific aspect word. When using the global attention mechanism to calculate the attention scores of attribute words and other words of the sentence, the model will focus on words that are not related to the attribute words, and pay insufficient attention to long-distance dependent words and negative words, and cannot detect side-by-side relationships or phrases. To solve these problems, this paper proposed a semantic enhancement model based on the self-attention mechanism(SRSAM). The model first used the bidirectional long short-term memory model to obtain the text encoding, and then used the self-attention mechanism to calculate the multiple semantic encodings of the text encoding. Finally, it used the attribute words and semantic coding to interact to determine the emotional polarity of the attribute words in the sentence. The experiment on the SemEval 2014 dataset show that, since the model can find long-distance dependence and negative words, it has a certain detection effect on the parallel relationship and the phrase, and the classification accuracy is 0.6%~1.5% higher than the basic model.
英文關鍵詞 aspect words; sentiment classification; self-attention mechanism; semantic coding
參考文獻 查看稿件參考文獻
 
收稿日期 2019/7/10
修回日期 2019/9/7
頁碼 3227-3231,3245
中圖分類號 TP391
文獻標志碼 A
福州麻将中什么叫金龙 三人麻将规则 福彩山西快乐十分开奖 宁夏吴忠11选5开奖结果 江西抚州金溪麻将优乐精麻将 亲朋棋牌官方下载 爱玩棋牌手机版作弊器 天津快乐10分基本走试图 贵州快3开奖查询 体彩十一运夺金前三 财神捕鱼为什么一直输 天狐河南麻将游戏下载 奇迹甘肃棋牌作弊器 北京快3人大小精准计划 河南11选5开奖直播 金蟾捕鱼大圣捕鱼 血流成河单机麻将下载