English

Learning Robust Named Entity Recognizers From Noisy Data With Retrieval Augmentation

Computation and Language 2024-07-29 v1 Artificial Intelligence

Abstract

Named entity recognition (NER) models often struggle with noisy inputs, such as those with spelling mistakes or errors generated by Optical Character Recognition processes, and learning a robust NER model is challenging. Existing robust NER models utilize both noisy text and its corresponding gold text for training, which is infeasible in many real-world applications in which gold text is not available. In this paper, we consider a more realistic setting in which only noisy text and its NER labels are available. We propose to retrieve relevant text of the noisy text from a knowledge corpus and use it to enhance the representation of the original noisy input. We design three retrieval methods: sparse retrieval based on lexicon similarity, dense retrieval based on semantic similarity, and self-retrieval based on task-specific text. After retrieving relevant text, we concatenate the retrieved text with the original noisy text and encode them with a transformer network, utilizing self-attention to enhance the contextual token representations of the noisy text using the retrieved text. We further employ a multi-view training framework that improves robust NER without retrieving text during inference. Experiments show that our retrieval-augmented model achieves significant improvements in various noisy NER settings.

Keywords

Cite

@article{arxiv.2407.18562,
  title  = {Learning Robust Named Entity Recognizers From Noisy Data With Retrieval Augmentation},
  author = {Chaoyi Ai and Yong Jiang and Shen Huang and Pengjun Xie and Kewei Tu},
  journal= {arXiv preprint arXiv:2407.18562},
  year   = {2024}
}
R2 v1 2026-06-28T17:54:19.446Z