On Extending Neural Networks with Loss Ensembles for Text Classification
This is an incremental improvement for text classification tasks, particularly in noisy label environments.
The paper tackled text classification by extending neural networks with an ensemble loss function, resulting in improved performance and strong resilience against label noise compared to other methods.
Ensemble techniques are powerful approaches that combine several weak learners to build a stronger one. As a meta learning framework, ensemble techniques can easily be applied to many machine learning techniques. In this paper we propose a neural network extended with an ensemble loss function for text classification. The weight of each weak loss function is tuned within the training phase through the gradient propagation optimization method of the neural network. The approach is evaluated on several text classification datasets. We also evaluate its performance in various environments with several degrees of label noise. Experimental results indicate an improvement of the results and strong resilience against label noise in comparison with other methods.