Aspect-Level Sentiment Classification with Conv-Attention Mechanism
Yi Qian; Liu Jie; Zhang Guixuan; Zhang Shuwu
Conference NameInternational Conference on Neural Information Processing (ICONIP)
Conference Date2018.12.13-2018.12.16
Conference PlaceSiem Reap, Cambodia

The aim of aspect-level sentiment classification is to identify the sentiment polarity of a sentence about a target aspect. Existing methods model the context sequence with recurrent network and employ attention mechanism to generate aspect-specific representations. In this paper, we introduce a novel mechanism called Conv-Attention, which can model the sequential information of context words and generate the aspect-specific attention at the same time via a convolution operation. Based on the new mechanism, we design a new framework for aspect-level sentiment classification called Conv-Attention Network (CAN). Compared to the previous attention-based recurrent models, the Conv-Attention Network can compute much faster. Extensive experimental results show that our model achieves the state-of-the-art performance while saving considerable time in model training and inferring.

Indexed ByEI
Document Type会议论文
Corresponding AuthorZhang Guixuan
Recommended Citation
GB/T 7714
Yi Qian,Liu Jie,Zhang Guixuan,et al. Aspect-Level Sentiment Classification with Conv-Attention Mechanism[C]:Springer,2018.
Files in This Item: Download All
File Name/Size DocType Version Access License
Aspect-Level Sentime(1027KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yi Qian]'s Articles
[Liu Jie]'s Articles
[Zhang Guixuan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yi Qian]'s Articles
[Liu Jie]'s Articles
[Zhang Guixuan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yi Qian]'s Articles
[Liu Jie]'s Articles
[Zhang Guixuan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Aspect-Level Sentiment Classification.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.