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.

翻译：不连续命名实体识别（DNER）提出了一个具有挑战性的问题，即实体可能分散在多个非相邻的标记中，这使得传统的序列标注方法难以应对。现有方法主要依赖自定义的标注方案来处理这些不连续实体，导致模型与特定的标注策略紧密耦合，且在不同数据集之间缺乏泛化能力。为了应对这些挑战，我们提出了TriG-NER，一种新颖的三元组网格框架，它引入了一种可泛化的方法来学习用于不连续实体提取的鲁棒标记级表示。我们的框架在标记级别应用三元组损失，其中相似性由存在于同一实体内的词对定义，从而有效地拉近相似词对并推远不相似词对。这种方法通过关注灵活网格结构内的词对关系，增强了实体边界检测能力，并减少了对特定标注方案的依赖。我们在三个基准DNER数据集上评估了TriG-NER，并证明其相较于现有基于网格的架构有显著改进。这些结果凸显了我们框架在捕捉复杂实体结构方面的有效性及其对各种标注方案的适应性，为不连续实体提取设立了新的基准。