Robust Text Classifier on Test-Time Budgets
This work addresses computational efficiency challenges in text classification for real-world applications, though it appears to be an incremental improvement on existing methods.
The authors tackled the problem of building efficient text classifiers under test-time computational constraints by developing a framework that learns to select relevant words for prediction tasks, achieving comparable accuracy to full models with minimal performance loss while significantly speeding up inference.
We propose a generic and interpretable learning framework for building robust text classification model that achieves accuracy comparable to full models under test-time budget constraints. Our approach learns a selector to identify words that are relevant to the prediction tasks and passes them to the classifier for processing. The selector is trained jointly with the classifier and directly learns to incorporate with the classifier. We further propose a data aggregation scheme to improve the robustness of the classifier. Our learning framework is general and can be incorporated with any type of text classification model. On real-world data, we show that the proposed approach improves the performance of a given classifier and speeds up the model with a mere loss in accuracy performance.