期刊名称：International Journal of Grid and Distributed Computing
印刷版ISSN：2005-4262
出版年度：2016
卷号：9
期号：11
页码：71-80
出版社：SERSC
摘要：Sentiment classification task has attracted considerable interest as sentiment information is crucial for many natural language processing (NLP) applications.The goal of sentiment classification is to predict the overall emotional polarity of a given text. Previous work has demonstrate the remarkable performance of Convolutional Neural Network (CNN). However, nearly all this work assumes a single word embedding for each word type, ignoring polysemy and thus inevitably casting negative impact on the downstream tasks. We extend the Skip-gram model to learn multiple sense embeddings for the word types, catering to introduce sense-based embeddings for CNN during sentiment classification. Instead of using the pipeline method to learn multiple sense embeddings of a word type, the sense discrimination and sense embedding learning for each word type are performed jointly based upon the semantics of its contextual words. We validate the effectiveness of the method on the commonly used datasets. Experiment results show that our method are able to improve the quality of sentiment classificationwhen comparing with several competitive baselines.
关键词：Natural Language Processing; ;Text Classification; ;Sense Sensitiv;e; ;Word ;Embedding
