Paper Info
Title
Learning With Annotation of Various Degrees.
Abstract
In this paper, we study a new problem in the scenario of sequences labeling. To be exact, we consider that the training data are with annotation of various degrees, namely, fully labeled, unlabeled, and partially labeled sequences. The learning with fully un/labeled sequence refers to the standard setting in traditional un/supervised learning, and the proposed partially labeling specifies the subject that the element does not belong to. The partially labeled data are cheaper to obtain compared with the fully labeled data though it is less informative, especially when the tasks require a lot of domain knowledge. To solve such a practical challenge, we propose a novel deep conditional random field (CRF) model which utilizes an end-to-end learning manner to smoothly handle fully/un/partially labeled sequences within a unified framework. To the best of our knowledge, this could be one of the first works to utilize the partially labeled instance for sequence labeling, and the proposed algorithm unifies the deep learning and CRF in an end-to-end framework. Extensive experiments show that our method achieves state-of-the-art performance in two sequence labeling tasks on some popular data sets.
Year
DOI
Venue
2019
10.1109/TNNLS.2018.2885854
IEEE transactions on neural networks and learning systems
Keywords
Field
DocType
Labeling,Supervised learning,Hidden Markov models,Training data,Semisupervised learning,Neural networks
Conditional random field,Annotation,Sequence labeling,Pattern recognition,Domain knowledge,Computer science,Supervised learning,Artificial intelligence,Deep learning,Hidden Markov model,Artificial neural network,Machine learning
Journal
Volume
Issue
ISSN
30
9
2162-2388
Citations 
PageRank 
References 
4
0.39
22
Authors
7
Name
Order
Citations
PageRank
Joey Tianyi Zhou135438.60
Meng Fang218313.52
Hao Zhang3143.59
Chen Gong440144.73
Xi Peng544723.84
Zhiguo Cao631444.17
Rick Siow Mong Goh733640.34