J. T. Zhou et al., "Learning With Annotation of Various Degrees," in IEEE Transactions on Neural Networks and Learning Systems, vol. 30, no. 9, pp. 2794-2804, Sept. 2019, doi: 10.1109/TNNLS.2018.2885854.
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 labelling tasks on some popular data sets.
License type:
PublisherCopyrights
Funding Info:
This work was supported in part by Singapore Government’s Research, Innovation and Enterprise 2020 Plan (Advanced Manufacturing and Engineering Domain) through programmatic under Grant A1687b0033, in part by the National Natural Science Foundation of China under Grant 61806135, Grant 61432012, Grant U1435213, Grant 61602246, and Grant 61876211, in part by the Fundamental Research Funds for the Central Universities under Grant YJ201748 and Grant 30918011319, in part by the NSF of Jiangsu Province under Grant BK20171430, in part by the Summit of the Six Top Talents Program under Grant DZXX-027, in part by the Lift Program for Young Talents of Jiangsu Province, and in part by the CAST Lift Program for Young Talents.