A Boundary Offset Prediction Network for Named Entity Recognition
This addresses a specific bottleneck in named entity recognition for natural language processing applications, with incremental improvements over existing methods.
The paper tackles the problem of imbalanced sample space and neglected connections between non-entity and entity spans in named entity recognition by proposing the Boundary Offset Prediction Network (BOPN), which predicts boundary offsets and integrates entity type representations, resulting in outperforming previous state-of-the-art methods on eight widely-used datasets.
Named entity recognition (NER) is a fundamental task in natural language processing that aims to identify and classify named entities in text. However, span-based methods for NER typically assign entity types to text spans, resulting in an imbalanced sample space and neglecting the connections between non-entity and entity spans. To address these issues, we propose a novel approach for NER, named the Boundary Offset Prediction Network (BOPN), which predicts the boundary offsets between candidate spans and their nearest entity spans. By leveraging the guiding semantics of boundary offsets, BOPN establishes connections between non-entity and entity spans, enabling non-entity spans to function as additional positive samples for entity detection. Furthermore, our method integrates entity type and span representations to generate type-aware boundary offsets instead of using entity types as detection targets. We conduct experiments on eight widely-used NER datasets, and the results demonstrate that our proposed BOPN outperforms previous state-of-the-art methods.