Semi-supervised Sentiment Classification Based on Auxiliary Task Learning

摘要：

　　Sentiment classification is an important task in the community of Nature Language Processing.This task aims to determine the sentiment category towards a piece of text.One challenging problem of this task is that it is difficult to obtain a large number of labeled samples.Therefore,a large number of studies are focused on semi-supervised learning,i.e.,learning information from unlabeled samples.However,one disadvantage of the previous methods is that the unlabeled samples and the labeled samples are studied in different models,and there is no interaction between them.Based on this,this paper tackles the problem by proposing a semi-supervised sentiment classification based on auxiliary task learning,namely Aux-LSTM,which is used to assist learning the sentiment classification task with a small amount of human-annotated samples by training auto-annotated samples.Specifically,the two tasks are allowed to share the auxiliary LSTM layer,and the auxiliary expression obtained by the auxiliary LSTM layer is used to assist the main task.Empirical studies demonstrate that the proposed method can effectively improve the experimental performance.

关键词： Sentiment classification Auxiliary task Auto-annotation samples

作者: Huan Liu Jingjing Wang Shoushan Li Junhui Li Guodong Zhou

作者单位: Natural Language Processing Lab,School of Computer Science and Technology,Soochow University,Suzhou,China

会议类型: 国际会议

会议名称: 2018自然语言处理与中文计算国际会议(NLPCC2018)

会议地点: 呼和浩特

会议语种:英文

页码: 372-382

在线出版日期: 2018-08-26（万方平台首次上网日期，不代表论文的发表时间）