Deep Active Learning for Text Classification with Diverse Interpretations | |
Liu, Qiang1,2; Zhu, Yanqiao1,2; liu, Zhaocheng3; Zhang, Yufeng1; Wu, Shu1,2 | |
2021-11 | |
会议名称 | ACM International Conference on Information and Knowledge Management |
会议日期 | 2021.11.01-2021.11.05 |
会议地点 | Queensland, Australia |
摘要 | 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. |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 数据挖掘 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/47491 |
专题 | 智能感知与计算研究中心 |
通讯作者 | Wu, Shu |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences 3.RealAI |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Liu, Qiang,Zhu, Yanqiao,liu, Zhaocheng,et al. Deep Active Learning for Text Classification with Diverse Interpretations[C],2021. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Deep Active Learning(1506KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论