点击次数：
论文类型：期刊论文
发表时间：2019-03-01
发表刊物：FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
收录刊物：SCIE、Scopus
卷号：92
页面范围：879-888
ISSN号：0167-739X
关键字：Sentiment analysis; Memory networks; Aspect-based Sentiment Classification; Attention mechanism
摘要：Sentiment analysis is an important research field in natural language processing. Aspect-based sentiment classification can efficiently solve fine-grained sentiment recognition, however, its classification accuracy becomes decreasing for large-scale corpus. To solve this problem, we propose a new memory network model, called Feature-based Compositing Memory Networks (FCMN). Differing from typical memory networks, we extract three kinds of features to enrich the word representation of each context word. We design compositing strategies combining feature representations and word embedding to improve the performance of attention mechanism. Experiments on laptops and restaurants datasets in SemEval 2014 show that our approach outperforms the feature-based SVM, TD-LSTM and Deep Memory Networks. Especially, FCMN gets better results with less hops than Deep Memory Networks. Experiments results demonstrate that FCMN can ignore words without sentiment and pay more attention on correct words in a sentence. (C) 2017 Elsevier B.V. All rights reserved.