Syntax-Aware Representation for Aspect Term Extraction

摘要：

　　Aspect Term Extraction(ATE)plays an important role in aspect-based sentiment analysis.Syntax-based neural models that learn rich linguistic knowledge have proven their effectiveness on ATE.However,previous approaches mainly focus on modeling syntactic structure,neglecting rich interactions along dependency arcs.Besides,these methods highly rely on results of dependency parsing and are sensitive to parsing noise.In this work,we introduce a syntax-directed attention network and a contextual gating mechanism to tackle these issues.Specifically,a graphical neural network is utilized to model interactions along dependency arcs.With the help of syntax-directed self-attention,it could directly operate on syntactic graph and obtain structural information.We further introduce a gating mechanism to synthesize syntactic information with structure-free features.This gate is utilized to reduce the effects of parsing noise.Experimental results demonstrate that the proposed method achieves state-of-the-art performance on three widely used benchmark datasets.

关键词： Aspect term extraction Syntactic information Gating mechanism

作者: Jingyuan Zhang Guangluan Xu Xinyi Wang Xian Sun Tinglei Huang

作者单位: Key Laboratory of Network Information System Technology(NIST),Institute of Electronics,Chinese Acade Key Laboratory of Network Information System Technology(NIST),Institute of Electronics,Chinese Acade

会议类型: 国际会议

会议名称: The 23rd Pacific-Asia Conference on Knowledge Discovery and Data Mining (第23届亚太知识发现和数据挖掘国际会议(PAKDD2019)

会议地点: 澳门

会议语种:英文

页码: 123-134

在线出版日期: 2019-04-14（万方平台首次上网日期，不代表论文的发表时间）