.png){kind=icon}
返回
Improving distantly supervised named entity recognition by emphasizing uncertain examples
.png){kind=icon}
PRE
AI
DOI：10.1007/s10044-024-01392-8.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Distantly supervised named entity recognition (DS-NER) aims to acquire knowledge from noisy labels. Recently, label re-weighting and label correction based frameworks have been recognized as promising approaches for DS-NER. These methods mainly handle easy or hard examples, yet neglect the impact of uncertain examples that are predicted correctly sometimes and incorrectly some other times during optimization. In this paper, we propose UE-NER, an Uncertainty Estimation method for DS-NER, which estimates the uncertainty of training examples and emphasizes uncertain ones, thus leads to more accurate and robust performance. To enable uncertainty reasoning, we formulate DS-NER as a span-level classification problem and the variance in predicted probability of the correct class across iterations of minibatch SGD is taken as the uncertainty measure. We further design an enhanced encoder to combine the power of the named entity and other spans in the sentence to boost recognition performance. Experimental results on two benchmark datasets demonstrate the superiority of the proposed UE-NER over existing DS-NER methods.
Keyword:
Named entity recognition
Distantly supervised
Uncertainty estimation
期刊
IF:
2
论文数:
1.9K
被引数:
1.9K
机构
引用论文
Transposase-Derived Transcription Factors Regulate Light Signaling in
Arabidopsis转座酶衍生的转录因子调节光信号
拟南芥 .png)
Science
OAAI
ScienceIF0
OAAI分享收藏Cervical small cell neuroendocrine tumor mutation profiles via whole exome sequencingOncotarget
OAAI
OncotargetIF0
OAAI分享收藏
查看更多内容