CLAIJul 26, 2024

Learning Robust Named Entity Recognizers From Noisy Data With Retrieval Augmentation

arXiv:2407.18562v12 citationsh-index: 30
Originality Incremental advance
AI Analysis

This addresses a practical limitation in real-world NER applications where gold text is unavailable, offering a more feasible approach for handling noisy inputs.

The paper tackles the problem of training robust named entity recognition models when only noisy text and labels are available, proposing retrieval-augmented methods that improve performance in noisy settings.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes