Convolution Neural Network with Active Learning for Information Extraction of Enterprise Announcements

扫码查看

原文链接

NETL
Springer Nature

外文摘要：We propose using convolution neural network (CNN) with active learning for information extraction of enterprise announcements。 The training process of supervised deep learning model usually requires a large amount of training data with high-quality reference samples。 Human production of such samples is tedious， and since inter-labeler agreement is low， very unreliable。 Active learning helps assuage this problem by automatically selecting a small amount of unlabeled samples for humans to hand correct。 Active learning chooses a selective set of samples to be labeled。 Then the CNN is trained on the labeled data iteratively， until the expected experimental effect is achieved。 We propose three sample selection methods based on certainty criterion。 We also establish an enterprise announcements dataset for experiments， which contains 10410 samples totally。 Our experiment results show that the amount of labeled data needed for a given extraction accuracy can be reduced by more than 45。79% compared to that without active learning。

外文关键词：

Text classificationActive learningConvolutional neural networksEnterprise announcements

作者：

Lei Fu、Zhaoxia Yin、Yi Liu、Jun Zhang

展开 >

作者单位：

Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui University, Hefei 230601, People's Republic of China,PKU Shenzhen Institute, Shenzhen, China

Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui University, Hefei 230601, People's Republic of China

PKU Shenzhen Institute, Shenzhen, China

Shenzhen Securities Information, Co., Ltd., Shenzhen, China

展开 >

会议名称：

CCF international conference on natural language processing and Chinese computing

会议地点：

Hohhot(CN)

会议母体文献：

Natural language processing and Chinese computing

页码：

330-339

出版时间：

2018

DOI：

10.1007/978-3-319-99501-4_29