Robust Text Classifier on Test-Time Budgets

TL;DR

This paper introduces a flexible, interpretable framework for robust text classification under test-time budget constraints, using a learned word selector and data aggregation to maintain accuracy and efficiency.

Contribution

It presents a novel joint training approach for a word selector and classifier, enhancing robustness and speed under resource constraints.

Findings

Improves classifier performance under test-time budgets

Speeds up models with minimal accuracy loss

Applicable to various text classification models

Abstract

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.