Universum Prescription: Regularization using Unlabeled DataUniversum Prescription: Regularization using Unlabeled DataZhang, Xiang and LeCun, Yann2015
Paper summaryevansuThis paper apply temporal convolutional neural network on character input to learn abstract text concepts. Depending on application, the model can output the category of text or review sentiment. The model is trained from character level and do not require knowledge of syntax or semantic structure. Therefore, the model can work for various language including English and Chinese with little prior knowledge of languages.