Enregistré dans:
Détails bibliographiques
Auteurs principaux: Sun, Mo, Xiong, Siheng, Cai, Yuankai, Zuo, Bowen
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2505.01868
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913819378319360
author Sun, Mo
Xiong, Siheng
Cai, Yuankai
Zuo, Bowen
author_facet Sun, Mo
Xiong, Siheng
Cai, Yuankai
Zuo, Bowen
contents This paper presents a framework for Named Entity Recognition (NER) leveraging the Bidirectional Encoder Representations from Transformers (BERT) model in natural language processing (NLP). NER is a fundamental task in NLP with broad applicability across downstream applications. While BERT has established itself as a state-of-the-art model for entity recognition, fine-tuning it from scratch for each new application is computationally expensive and time-consuming. To address this, we propose a cost-efficient approach that integrates positional attention mechanisms into the entity recognition process and enables effective customization using pre-trained parameters. The framework is evaluated on a Kaggle dataset derived from the Groningen Meaning Bank corpus and achieves strong performance with fewer training epochs. This work contributes to the field by offering a practical solution for reducing the training cost of BERT-based NER systems while maintaining high accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2505_01868
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Positional Attention for Efficient BERT-Based Named Entity Recognition
Sun, Mo
Xiong, Siheng
Cai, Yuankai
Zuo, Bowen
Computation and Language
This paper presents a framework for Named Entity Recognition (NER) leveraging the Bidirectional Encoder Representations from Transformers (BERT) model in natural language processing (NLP). NER is a fundamental task in NLP with broad applicability across downstream applications. While BERT has established itself as a state-of-the-art model for entity recognition, fine-tuning it from scratch for each new application is computationally expensive and time-consuming. To address this, we propose a cost-efficient approach that integrates positional attention mechanisms into the entity recognition process and enables effective customization using pre-trained parameters. The framework is evaluated on a Kaggle dataset derived from the Groningen Meaning Bank corpus and achieves strong performance with fewer training epochs. This work contributes to the field by offering a practical solution for reducing the training cost of BERT-based NER systems while maintaining high accuracy.
title Positional Attention for Efficient BERT-Based Named Entity Recognition
topic Computation and Language
url https://arxiv.org/abs/2505.01868