TriG-NER: Triplet-Grid Framework for Discontinuous Named Entity Recognition

2024-11-04

arXiv.org

AI Summary

Discontinuous named entity recognition (DNER) poses significant challenges in modeling entities that span non-contiguous text segments and exhibit discontinuity. Method: This paper proposes a label-schema-agnostic word-pair relational modeling paradigm: we construct a triplet grid to encode intra- and inter-entity token-level similarities, and introduce a novel token-level triplet loss for end-to-end optimization. Our approach decouples entity boundary detection from rigid labeling-format constraints, enabling fine-grained and robust representation learning. Contribution/Results: Evaluated on three mainstream DNER benchmarks, our method consistently outperforms existing grid-based approaches, achieving substantial improvements in recognizing cross-segment and nested entities. Moreover, it natively supports diverse annotation schemas—demonstrating strong generalizability and superior structural modeling capability.

Technology Category

• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.
• Reasoning under Uncertainty: Relational Probabilistic Models
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Discontinuous Named Entity Recognition (DNER) presents a challenging problem where entities may be scattered across multiple non-adjacent tokens, making traditional sequence labelling approaches inadequate. Existing methods predominantly rely on custom tagging schemes to handle these discontinuous entities, resulting in models tightly coupled to specific tagging strategies and lacking generalisability across diverse datasets. To address these challenges, we propose TriG-NER, a novel Triplet-Grid Framework that introduces a generalisable approach to learning robust token-level representations for discontinuous entity extraction. Our framework applies triplet loss at the token level, where similarity is defined by word pairs existing within the same entity, effectively pulling together similar and pushing apart dissimilar ones. This approach enhances entity boundary detection and reduces the dependency on specific tagging schemes by focusing on word-pair relationships within a flexible grid structure. We evaluate TriG-NER on three benchmark DNER datasets and demonstrate significant improvements over existing grid-based architectures. These results underscore our framework's effectiveness in capturing complex entity structures and its adaptability to various tagging schemes, setting a new benchmark for discontinuous entity extraction.

Problem

• Discontinuous Named Entity Recognition
• DNER
• Challenges

Innovation

• TriG-NER
• Triplet Loss
• Discontinuous Entity Recognition