Nested Named Entity Recognition as Single-Pass Sequence Labeling

2025-05-22

AI Summary

This work addresses the challenges of high computational complexity and structural intricacy in nested named entity recognition (NNER). We propose a single-pass sequence labeling approach that linearizes nested entity structures—represented as constituent trees—into token-level label sequences, thereby achieving the first complete reduction of NNER to standard token classification. Unlike prior methods, our approach eliminates the need for span enumeration, hierarchical decoding, or graph-based modeling; instead, it relies solely on a pretrained encoder (e.g., BERT) and a lightweight linearization strategy, ensuring seamless integration with mainstream sequence labeling frameworks. Crucially, it preserves expressive power while reducing inference time complexity to *O(n)*, significantly improving training and deployment efficiency. Extensive experiments demonstrate state-of-the-art performance across multiple benchmarks, validating the method’s effectiveness, simplicity, and strong generalization capability.

Technology Category

Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.Machine Learning: Structured LearningKnowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphsSemantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMsSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

We cast nested named entity recognition (NNER) as a sequence labeling task by leveraging prior work that linearizes constituency structures, effectively reducing the complexity of this structured prediction problem to straightforward token classification. By combining these constituency linearizations with pretrained encoders, our method captures nested entities while performing exactly $n$ tagging actions. Our approach achieves competitive performance compared to less efficient systems, and it can be trained using any off-the-shelf sequence labeling library.

Problem

• Reduces nested NER to sequence labeling
• Uses constituency linearizations with pretrained encoders
• Achieves competitive performance efficiently

Innovation

• Linearizes constituency structures for sequence labeling
• Combines linearizations with pretrained encoders
• Achieves competitive performance efficiently