A Boundary Offset Prediction Network for Named Entity Recognition

Minghao Tang, Yongquan He, Yongxiu Xu, Hongbo Xu, Wenyuan Zhang, Yang Lin

Submission Type: Regular Long Paper

Submission Track: Information Extraction

Submission Track 2: Efficient Methods for NLP

Keywords: named entity recognition, span-based methods, boundary connections, boundary offset prediction network, type-related boundary offsets

TL;DR: This paper presents the Boundary Offset Prediction Network (BOPN), a novel approach for NER that predicts the boundary offsets between candidate spans and their nearest entity spans.

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.

Submission Number: 640