CASIA OpenIR  > 模式识别实验室
Deep Active Learning for Text Classification with Diverse Interpretations
Liu, Qiang1,2; Zhu, Yanqiao1,2; liu, Zhaocheng3; Zhang, Yufeng1; Wu, Shu1,2
2021-11
Conference NameACM International Conference on Information and Knowledge Management
Conference Date2021.11.01-2021.11.05
Conference PlaceQueensland, Australia
Abstract

Recently, Deep Neural Networks (DNNs) have made remarkable progress for text classification, which, however, still require a large number of labeled data. To train high-performing models with the minimal annotation cost, active learning is proposed to select and label the most informative samples, yet it is still challenging to measure informativeness of samples used in DNNs. In this paper, inspired by piece-wise linear interpretability of DNNs, we propose a novel Active Learning with DivErse iNterpretations (ALDEN) approach. With local interpretations in DNNs, ALDEN identifies linearly separable regions of samples. Then, it selects samples according to their diversity of local interpretations and queries their labels. To tackle the text classification problem, we choose the word with the most diverse interpretations to represent the whole sentence. Extensive experiments demonstrate that ALDEN consistently outperforms several state-of-the-art deep active learning methods.

Indexed ByEI
Language英语
Sub direction classification数据挖掘
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/47491
Collection模式识别实验室
Corresponding AuthorWu, Shu
Affiliation1.Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
3.RealAI
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Liu, Qiang,Zhu, Yanqiao,liu, Zhaocheng,et al. Deep Active Learning for Text Classification with Diverse Interpretations[C],2021.
Files in This Item:
File Name/Size DocType Version Access License
Deep Active Learning(1506KB)会议论文 开放获取CC BY-NC-SAView
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Liu, Qiang]'s Articles
[Zhu, Yanqiao]'s Articles
[liu, Zhaocheng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Liu, Qiang]'s Articles
[Zhu, Yanqiao]'s Articles
[liu, Zhaocheng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Liu, Qiang]'s Articles
[Zhu, Yanqiao]'s Articles
[liu, Zhaocheng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Deep Active Learning for Text Classification with Diverse Interpretations.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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