Learning with Noisy Labels for Sentence-level Sentiment Classification
This addresses the issue of noisy labels in sentiment classification, which can degrade model performance, but it appears incremental as it builds on existing methods for handling label noise.
The paper tackles the problem of training deep neural networks on data with noisy labels for sentence-level sentiment classification, proposing a novel model called NetAb that uses two convolutional networks trained with mutual reinforcement, which demonstrates effectiveness in experiments.
Deep neural networks (DNNs) can fit (or even over-fit) the training data very well. If a DNN model is trained using data with noisy labels and tested on data with clean labels, the model may perform poorly. This paper studies the problem of learning with noisy labels for sentence-level sentiment classification. We propose a novel DNN model called NetAb (as shorthand for convolutional neural Networks with Ab-networks) to handle noisy labels during training. NetAb consists of two convolutional neural networks, one with a noise transition layer for dealing with the input noisy labels and the other for predicting 'clean' labels. We train the two networks using their respective loss functions in a mutual reinforcement manner. Experimental results demonstrate the effectiveness of the proposed model.