Are Data Augmentation Methods in Named Entity Recognition Applicable for Uncertainty Estimation?

TL;DR

This paper explores how data augmentation techniques can enhance confidence calibration and uncertainty estimation in Named Entity Recognition, especially in cross-genre, cross-lingual, and in-domain scenarios, aiding safe deployment of NLP models.

Contribution

It demonstrates that data augmentation improves calibration and uncertainty estimation in NER, with effectiveness linked to sentence perplexity and augmentation size.

Findings

Data augmentation improves calibration in NER tasks.

Lower perplexity in augmented sentences leads to better calibration.

Increasing augmentation size further enhances calibration and uncertainty estimation.

Abstract

This work investigates the impact of data augmentation on confidence calibration and uncertainty estimation in Named Entity Recognition (NER) tasks. For the future advance of NER in safety-critical fields like healthcare and finance, it is essential to achieve accurate predictions with calibrated confidence when applying Deep Neural Networks (DNNs), including Pre-trained Language Models (PLMs), as a real-world application. However, DNNs are prone to miscalibration, which limits their applicability. Moreover, existing methods for calibration and uncertainty estimation are computational expensive. Our investigation in NER found that data augmentation improves calibration and uncertainty in cross-genre and cross-lingual setting, especially in-domain setting. Furthermore, we showed that the calibration for NER tends to be more effective when the perplexity of the sentences generated by data augmentation is lower, and that increasing the size of the augmentation further improves calibration and uncertainty.