From Random to Supervised: A Novel Dropout Mechanism Integrated with Global Information
This work addresses overfitting in text classification for researchers and practitioners, but it is incremental as it builds on the well-established dropout technique.
The paper tackles overfitting in neural networks by introducing GI-Dropout, a method that uses global dataset information to guide dropout instead of random dropping, resulting in improved performance on seven text classification tasks such as sentiment analysis and topic classification.
Dropout is used to avoid overfitting by randomly dropping units from the neural networks during training. Inspired by dropout, this paper presents GI-Dropout, a novel dropout method integrating with global information to improve neural networks for text classification. Unlike the traditional dropout method in which the units are dropped randomly according to the same probability, we aim to use explicit instructions based on global information of the dataset to guide the training process. With GI-Dropout, the model is supposed to pay more attention to inapparent features or patterns. Experiments demonstrate the effectiveness of the dropout with global information on seven text classification tasks, including sentiment analysis and topic classification.