%0 Generic %1 wu2018reinforced %A Wu, Jiawei %A Li, Lei %A Wang, William Yang %D 2018 %K semisup %T Reinforced Co-Training %U http://arxiv.org/abs/1804.06035 %X Co-training is a popular semi-supervised learning framework to utilize a large amount of unlabeled data in addition to a small labeled set. Co-training methods exploit predicted labels on the unlabeled data and select samples based on prediction confidence to augment the training. However, the selection of samples in existing co-training methods is based on a predetermined policy, which ignores the sampling bias between the unlabeled and the labeled subsets, and fails to explore the data space. In this paper, we propose a novel method, Reinforced Co-Training, to select high-quality unlabeled samples to better co-train on. More specifically, our approach uses Q-learning to learn a data selection policy with a small labeled dataset, and then exploits this policy to train the co-training classifiers automatically. Experimental results on clickbait detection and generic text classification tasks demonstrate that our proposed method can obtain more accurate text classification results.

@misc{wu2018reinforced, abstract = {Co-training is a popular semi-supervised learning framework to utilize a large amount of unlabeled data in addition to a small labeled set. Co-training methods exploit predicted labels on the unlabeled data and select samples based on prediction confidence to augment the training. However, the selection of samples in existing co-training methods is based on a predetermined policy, which ignores the sampling bias between the unlabeled and the labeled subsets, and fails to explore the data space. In this paper, we propose a novel method, Reinforced Co-Training, to select high-quality unlabeled samples to better co-train on. More specifically, our approach uses Q-learning to learn a data selection policy with a small labeled dataset, and then exploits this policy to train the co-training classifiers automatically. Experimental results on clickbait detection and generic text classification tasks demonstrate that our proposed method can obtain more accurate text classification results.}, added-at = {2018-05-07T10:08:46.000+0200}, author = {Wu, Jiawei and Li, Lei and Wang, William Yang}, biburl = {https://www.bibsonomy.org/bibtex/228a080e83de35b95786c133b897666e1/topel}, interhash = {bbac65bd7647923fa4084d473f989a00}, intrahash = {28a080e83de35b95786c133b897666e1}, keywords = {semisup}, note = {cite arxiv:1804.06035Comment: 11 pages, 3 figures. Accepted to NAACL 2018}, timestamp = {2018-05-07T10:09:16.000+0200}, title = {Reinforced Co-Training}, url = {http://arxiv.org/abs/1804.06035}, year = 2018 }