Conformal Predictor for Improving Zero-Shot Text Classification Efficiency

Prafulla Kumar Choubey, Yu Bai, Chien-Sheng Wu, Wenhao Liu, Nazneen Rajani

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%.
Anthology ID:
2022.emnlp-main.196
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3027–3034
Language:
URL:
https://aclanthology.org/2022.emnlp-main.196
DOI:
Bibkey:
Cite (ACL):
Prafulla Kumar Choubey, Yu Bai, Chien-Sheng Wu, Wenhao Liu, and Nazneen Rajani. 2022. Conformal Predictor for Improving Zero-Shot Text Classification Efficiency. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3027–3034, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Conformal Predictor for Improving Zero-Shot Text Classification Efficiency (Choubey et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.emnlp-main.196.pdf
PDF Search