Learning With Annotation of Various Degrees

• Published in: IEEE transaction on neural networks and learning systems Vol. 30; no. 9; pp. 2794 - 2804
• Main Authors: Zhou, Joey Tianyi, Fang, Meng, Zhang, Hao, Gong, Chen, Peng, Xi, Cao, Zhiguo, Goh, Rick Siow Mong
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Annotations; Conditional random fields; Deep conditional random field (CRF); Hidden Markov models; incomplete annotation; Labeling; Labelling; Machine learning; Neural networks; partially labeled data; Semisupervised learning; sequence labeling; Supervised learning; Training data
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2018.2885854

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.