Research on Pattern Representation and Reliability in Semi-Supervised Entity Relation Extraction

2016 ◽  
pp. 289-297 ◽  
Author(s):  
Feiyue Ye ◽  
Nan Tang
Keyword(s):  
Relation Extraction ◽  
Entity Relation Extraction

Entity Relation Extraction from News Articles in Portuguese for Competitive Intelligence Based on BERT

2021 ◽  
pp. 449-464
Author(s):  
Daniel De Los Reyes ◽  
Douglas Trajano ◽  
Isabel Harb Manssour ◽  
Renata Vieira ◽  
Rafael H. Bordini
Keyword(s):  
Relation Extraction ◽  
Competitive Intelligence ◽  
Entity Relation Extraction

Research on the Entity Relation Extraction of Field Based on Semi-Supervised

2011 ◽  
Vol 225-226 ◽  
pp. 1292-1300
Author(s):  
Jian Yi Guo ◽  
Jun Zhao ◽  
Zheng Tao Yu ◽  
Lei Su ◽  
Yan Tuan Xian ◽  
...  
Keyword(s):  
Supervised Learning ◽  
Information Entropy ◽  
Rate Increase ◽  
Relation Extraction ◽  
Classification Performance ◽  
Training Data ◽  
Small Scale ◽  
Result Show ◽  
Entity Relation Extraction ◽  
Precision Rate

Aim at the problem of supervised learning needing much labeled data for training, this paper proposes a new method based on Semi-Supervised learning. Firstly, to construct a classifier of certain accuracy, small-scale training data was used.Secondly, with the self-expanding idea, we applied the method of information entropy to select some new instances of higher credibility from candidate instances, which were to be predicted by the classifier. Finally, with the expansion of training data, training classifier re-iteratively, classification performance tended to be stable iteration termination, which achieved the entity relation extraction of tourism field by semi-supervised learning. The experiments result show that the new classifier which applies information entropy to iteratively expand training data to be trained makes the precision rate increase by 7% and the F-score increase by 15%.

Sign in / Sign up

Export Citation Format

Share Document