Conformal Predictor for Improving Zero-shot Text Classification Efficiency
This work addresses efficiency improvements for zero-shot text classification, which is incremental as it builds on existing cross-encoder methods.
The paper tackles the high computational cost of zero-shot text classification models by using a conformal predictor to restrict the number of likely labels, reducing average inference time by 25.6% for NLI-based models and 22.2% for NSP-based models without dropping performance below a 1% error rate.
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%.