A Boundary Offset Prediction Network for Named Entity Recognition

TL;DR

This paper introduces BOPN, a novel NER model that predicts boundary offsets to better connect entity and non-entity spans, improving detection accuracy across multiple datasets.

Contribution

BOPN is the first to use boundary offset prediction for NER, enhancing span connections and incorporating type-aware offsets for improved performance.

Findings

BOPN outperforms previous state-of-the-art methods on eight datasets.

Boundary offset prediction effectively links non-entity and entity spans.

Type-aware boundary offsets improve entity detection accuracy.

Abstract

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.