Mitigating Out-of-Entity Errors in Named Entity Recognition: A Sentence-Level Strategy

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Guochao, Luo, Ziqin, Hu, Chengwei, Ding, Zepeng, Yang, Deqing
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916563858227200
author Jiang, Guochao
Luo, Ziqin
Hu, Chengwei
Ding, Zepeng
Yang, Deqing
author_facet Jiang, Guochao
Luo, Ziqin
Hu, Chengwei
Ding, Zepeng
Yang, Deqing
contents Many previous models of named entity recognition (NER) suffer from the problem of Out-of-Entity (OOE), i.e., the tokens in the entity mentions of the test samples have not appeared in the training samples, which hinders the achievement of satisfactory performance. To improve OOE-NER performance, in this paper, we propose a new framework, namely S+NER, which fully leverages sentence-level information. Our S+NER achieves better OOE-NER performance mainly due to the following two particular designs. 1) It first exploits the pre-trained language model's capability of understanding the target entity's sentence-level context with a template set. 2) Then, it refines the sentence-level representation based on the positive and negative templates, through a contrastive learning strategy and template pooling method, to obtain better NER results. Our extensive experiments on five benchmark datasets have demonstrated that, our S+NER outperforms some state-of-the-art OOE-NER models.
format Preprint
id arxiv_https___arxiv_org_abs_2412_08434
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mitigating Out-of-Entity Errors in Named Entity Recognition: A Sentence-Level Strategy
Jiang, Guochao
Luo, Ziqin
Hu, Chengwei
Ding, Zepeng
Yang, Deqing
Computation and Language
Artificial Intelligence
Many previous models of named entity recognition (NER) suffer from the problem of Out-of-Entity (OOE), i.e., the tokens in the entity mentions of the test samples have not appeared in the training samples, which hinders the achievement of satisfactory performance. To improve OOE-NER performance, in this paper, we propose a new framework, namely S+NER, which fully leverages sentence-level information. Our S+NER achieves better OOE-NER performance mainly due to the following two particular designs. 1) It first exploits the pre-trained language model's capability of understanding the target entity's sentence-level context with a template set. 2) Then, it refines the sentence-level representation based on the positive and negative templates, through a contrastive learning strategy and template pooling method, to obtain better NER results. Our extensive experiments on five benchmark datasets have demonstrated that, our S+NER outperforms some state-of-the-art OOE-NER models.
title Mitigating Out-of-Entity Errors in Named Entity Recognition: A Sentence-Level Strategy
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2412.08434