Conformal Predictor for Improving Zero-shot Text Classification Efficiency

TL;DR

This paper introduces a conformal predictor to efficiently narrow down candidate labels in zero-shot text classification, significantly reducing inference time while maintaining high accuracy.

Contribution

It proposes a novel use of conformal prediction to improve the efficiency of cross-encoder zero-shot models without sacrificing performance.

Findings

Inference time reduced by over 22% on multiple datasets.

Prediction sets maintain 99% coverage, ensuring high reliability.

Method applicable to intent and topic classification tasks.

Abstract

Pre-trained language models (PLMs) have been shown effective for zero-shot (0shot) text classification. 0shot models based on natural language inference (NLI) and next sentence prediction (NSP) employ cross-encoder architecture and infer by making a forward pass through the model for each label-text pair separately. This increases the computational cost to make inferences linearly in the number of labels. In this work, we improve the efficiency of such cross-encoder-based 0shot models by restricting the number of likely labels using another fast base classifier-based conformal predictor (CP) calibrated on samples labeled by the 0shot model. Since a CP generates prediction sets with coverage guarantees, it reduces the number of target labels without excluding the most probable label based on the 0shot model. We experiment with three intent and two topic classification datasets. With a suitable CP for each dataset, we reduce the average inference time for NLI- and NSP-based models by 25.6% and 22.2% respectively, without dropping performance below the predefined error rate of 1%.