# AUC Maximization for Low-Resource Named Entity Recognition

arXiv: https://arxiv.org/abs/2212.04800 · HTML: https://mlsanity.com/paper/2212.04800/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 48 references that are in the map.
- First posted on arXiv 9 Dec 2022.

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [Neural Architectures for Named Entity Recognition](https://mlsanity.com/paper/1603.01360/) (2016)
- [Bidirectional LSTM-CRF Models for Sequence Tagging](https://mlsanity.com/paper/1508.01991/) (2015)
- [A Survey on Deep Learning for Named Entity Recognition](https://mlsanity.com/paper/1812.09449/) (2018)
- [Dice Loss for Data-imbalanced NLP Tasks](https://mlsanity.com/paper/1911.02855/) (2019)
- [A Survey on Recent Advances in Named Entity Recognition from Deep Learning models](https://mlsanity.com/paper/1910.11470/) (2019)
- [Stochastic AUC Maximization with Deep Neural Networks](https://mlsanity.com/paper/1908.10831/) (2019)
- [One-Pass AUC Optimization](https://mlsanity.com/paper/1305.1363/) (2013)
- [MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NER](https://mlsanity.com/paper/2108.13655/) (2021)
- [Learning with Multiclass AUC: Theory and Algorithms](https://mlsanity.com/paper/2107.13171/) (2021)
- [Diversity Enhanced Active Learning with Strictly Proper Scoring Rules](https://mlsanity.com/paper/2110.14171/) (2021)
- [Data Augmentation for Cross-Domain Named Entity Recognition](https://mlsanity.com/paper/2109.01758/) (2021)
- [Hardness-guided domain adaptation to recognise biomedical named entities under low-resource scenarios](https://mlsanity.com/paper/2211.05980/) (2022)

## Built on by (most cited first, 6 of 6)

- [How Can I Improve? Using GPT to Highlight the Desired and Undesired Parts of Open-ended Responses](https://mlsanity.com/paper/2405.00291/) (2024)
- [Using Large Language Models to Provide Explanatory Feedback to Human Tutors](https://mlsanity.com/paper/2306.15498/) (2023)
- [Informed Named Entity Recognition Decoding for Generative Language Models](https://mlsanity.com/paper/2308.07791/) (2023)
- [Robust Educational Dialogue Act Classifiers with Low-Resource and Imbalanced Datasets](https://mlsanity.com/paper/2304.07499/) (2023)
- [Low-Resource Named Entity Recognition: Can One-vs-All AUC Maximization Help?](https://mlsanity.com/paper/2311.04918/) (2023)
- [EIoU-EMC: A Novel Loss for Domain-specific Nested Entity Recognition](https://mlsanity.com/paper/2504.14203/) (2025)

## Abstract (arXiv)

Current work in named entity recognition (NER) uses either cross entropy (CE) or conditional random fields (CRF) as the objective/loss functions to optimize the underlying NER model. Both of these traditional objective functions for the NER problem generally produce adequate performance when the data distribution is balanced and there are sufficient annotated training examples. But since NER is inherently an imbalanced tagging problem, the model performance under the low-resource settings could suffer using these standard objective functions. Based on recent advances in area under the ROC curve (AUC) maximization, we propose to optimize the NER model by maximizing the AUC score. We give evidence that by simply combining two binary-classifiers that maximize the AUC score, significant performance improvement over traditional loss functions is achieved under low-resource NER settings. We also conduct extensive experiments to demonstrate the advantages of our method under the low-resource and highly-imbalanced data distribution settings. To the best of our knowledge, this is the first work that brings AUC maximization to the NER setting. Furthermore, we show that our method is agnostic to different types of NER embeddings, models and domains. The code to replicate this work will be provided upon request.