Densely-connected neural networks for aspect term extraction

作     者：Chen CHEN Houfeng WANG Qingqing ZHU Junfei LIU Chen CHEN;Houfeng WANG;Qingqing ZHU;Junfei LIU

作者机构：School of Software and Microelectronics Peking University MOE Key Lab of Computational Linguistics School of Electronics Engineering and Computer SciencePeking University National Engineering Research Center for Software Engineering (Peking University) 

出 版 物：《Science China(Information Sciences)》 (中国科学:信息科学(英文版))

年 卷 期：2022年第65卷第6期

页      面：264-266页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 0808[工学-电气工程] 081203[工学-计算机应用技术] 08[工学] 081104[工学-模式识别与智能系统] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by National Natural Science Foundation of China (Grant No. 61433015) 

主　　题：aspect term extraction recurrent neural network self-attention densely-connected network double word embeddings Aspect-Based Sentiment Analysis deep learning sequence labeling 

摘      要：Dear editor,Aspect term extraction(ATE) is a sub-task of aspect-based sentiment analysis, which aims to extract opinionated aspect terms from user reviews. For example, in a laptop domain review: “Boot time is super fast, boot time is an aspect, and the sentiment towards it is positive, which can be inferred from super fast.