CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
Reading selectively via Binary Input Gated Recurrent Unit
Li Z(李哲); Wang PS(王培松); Lu HQ(卢汉清); Cheng J(程健)
2019-08
Conference NameInternational Joint Conference on Artificial Intelligence
Conference Date2019-08
Conference Place中国澳门
Abstract

Recurrent Neural Networks (RNNs) have shown great promise in sequence modeling tasks. Gated Recurrent Unit (GRU) is one of the most used recurrent structures, which makes a good trade-off between performance and time spent. However, its practical implementation based on soft gates only partially achieves the goal to control information flow. We can hardly explain what the network has learnt internally. Inspired by human reading, we introduce binary input gated recurrent unit (BIGRU), a GRU based model using a binary input gate instead of the reset gate in GRU. By doing so, our model can read selectively during interference. In our experiments, we show that BIGRU mainly ignores the conjunctions, adverbs and articles that do not make a big difference to the document understanding, which is meaningful for us to further understand how the network works. In addition, due to reduced interference from redundant information, our model achieves better performances than baseline GRU in all the testing tasks.

Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23693
Collection模式识别国家重点实验室_图像与视频分析
Corresponding AuthorLi Z(李哲)
Affiliation中国科学院自动化研究所
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Li Z,Wang PS,Lu HQ,et al. Reading selectively via Binary Input Gated Recurrent Unit[C],2019.
Files in This Item:
File Name/Size DocType Version Access License
ijcai19.pdf(1207KB)会议论文 开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li Z(李哲)]'s Articles
[Wang PS(王培松)]'s Articles
[Lu HQ(卢汉清)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li Z(李哲)]'s Articles
[Wang PS(王培松)]'s Articles
[Lu HQ(卢汉清)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li Z(李哲)]'s Articles
[Wang PS(王培松)]'s Articles
[Lu HQ(卢汉清)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: ijcai19.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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