arrow
Return

Substructural Regularization With Data-Sensitive Granularity for Sequence Transfer Learning

delete2018-06-01
delete12
PRE
AI
孙
孙世昌 (Shichang Sun) *
H
Hongbo Liu
J
Jiana Meng
陈晨 cover
陈晨 (C. L. Philip Chen)
Y
Yu Yang
DOI:10.1109/TNNLS.2016.2638321delete
deleteOriginal
deleteShare
deleteSave
Abstract

Abstract

En 中文
Sequence transfer learning is of interest in both academia and industry with the emergence of numerous new text domains from Twitter and other social media tools. In this paper, we put forward the data-sensitive granularity for transfer learning, and then, a novel substructural regularization transfer learning model (STLM) is proposed to preserve target domain features at substructural granularity in the light of the condition of labeled data set size. Our model is underpinned by hidden Markov model and regularization theory, where the substructural representation can be integrated as a penalty after measuring the dissimilarity of substructures between target domain and STLM with relative entropy. STLM can achieve the competing goals of preserving the target domain substructure and utilizing the observations from both the target and source domains simultaneously. The estimation of STLM is very efficient since an analytical solution can be derived as a necessary and sufficient condition. The relative usability of substructures to act as regularization parameters and the time complexity of STLM are also analyzed and discussed. Comprehensive experiments of part-of-speech tagging with both Brown and Twitter corpora fully justify that our model can make improvements on all the combinations of source and target domains.
Keywords:
Data-sensitive granularity
hidden Markov model (HMM)
relative entropy (RE)
sequence transfer learning
substructural regularization

Journal

IEEE Transactions on Neural Networks and Learning Systems cover
IEEE Transactions on Neural Networks and Learning Systems
IF:
8.9
Papers:
7.8K
Citations:
9.0W

Organization

dalian maritime university cover
dalian maritime university
Scholars:
2.1K
Papers: 612
Citations: 6.1K
dalian university of technology cover
dalian university of technology
Scholars:
6.5K
Papers: 1.8K
Citations: 3.5W
U
University of Macau
Scholars:
1.5K
Papers: 706
Citations: 1.2W
researcher View more organizations
Cited Papers

Cited Papers

The Friction and Lubrication of elastomers
err1995-01-01
err0
PREAI
errA. Arvanitaki; B.J. Briscoe; M.J. Adams; S.A. Johnson
errShare
errSave
errShare
errSave
Triplex Transfer Learning: Exploiting Both Shared and Distinct Concepts for Text Classification
err2014-07-01
err56
PREAI
errZhuang, Fuzhen; Luo, Ping; Du, Changying; He, Qing; Shi, Zhongzhi; Xiong, Hui
errShare
errSave
researcher View more