期刊
NEUROCOMPUTING
卷 383, 期 -, 页码 336-347出版社
ELSEVIER
DOI: 10.1016/j.neucom.2019.12.035
关键词
Aspect embedding; Sentiment analysis; Representation learning
资金
- Fundamental Research Funds for the Central Universities, SCUT [2017ZD048, D2182480]
- Science and Technology Planning Project of Guangdong Province [2017B050506004]
- Science and Technology Programs of Guangzhou [201704030076, 201802010027]
- CUHK Research Committee Funding [EE16963]
- Hong Kong Research Grants Council [C1031-18G]
Aspect-Based Sentiment Analysis (ABSA) is a fine-grained sentiment analysis task, which aims to predict sentiment polarities of given aspects or target terms in text. ABSA contains two subtasks: Aspect-Category Sentiment Analysis (ACSA) and Aspect-Term Sentiment Analysis (ATSA). Aspect embeddings have been extensively used for representing aspect-categories on ACSA task. Based on our observations, existing aspect embeddings cannot properly represent the relation between aspect-categories and aspect-terms. To address this limitation, this paper presents a learning method which trains aspect embeddings according to the relation between aspect-categories and aspect-terms. According to the cosine measure metric we proposed in this paper, the limitation is successfully alleviated in the aspect embeddings which are trained by our method. The trained aspect embeddings can be used as initialization in existing models to solve ACSA task. We conduct experiments on SemEval datasets for ACSA task, and the results indicate that our pre-trained aspect embeddings are capable of improving the performance of sentiment analysis. (C) 2019 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据