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

PDF

Guochao Jiang , Ziqin Luo , Chengwei Hu , Zepeng Ding , Deqing Yang ·

YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2412.08434

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.

Related Topics

Computer Science

Artificial Intelligence

Engineering

Systems Engineering

Knowledge Base

Concepts

Named-entity recognition Entity linking Computer science Sentence Natural language processing Artificial intelligence Speech recognition Engineering Systems engineering Knowledge base Task (project management)

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2412.08434
PDF: https://arxiv.org/pdf/2412.08434
OA Status: green
Cited By: 1
Related Works: 10
OpenAlex ID: https://openalex.org/W4405306753

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4405306753

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2412.08434

Digital Object Identifier
Title: Mitigating Out-of-Entity Errors in Named Entity Recognition: A Sentence-Level Strategy

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2024

Year of publication
Publication date: 2024-12-11

Full publication date if available
Authors: Guochao Jiang, Ziqin Luo, Chengwei Hu, Zepeng Ding, Deqing Yang

List of authors in order
Landing page: https://arxiv.org/abs/2412.08434

Publisher landing page
PDF URL: https://arxiv.org/pdf/2412.08434

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2412.08434

Direct OA link when available
Concepts: Named-entity recognition, Entity linking, Computer science, Sentence, Natural language processing, Artificial intelligence, Speech recognition, Engineering, Systems engineering, Knowledge base, Task (project management)

Top concepts (fields/topics) attached by OpenAlex
Cited by: 1

Total citation count in OpenAlex
Citations by year (recent): 2025: 1

Per-year citation counts (last 5 years)
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4405306753
doi	https://doi.org/10.48550/arxiv.2412.08434
ids.doi	https://doi.org/10.48550/arxiv.2412.08434
ids.openalex	https://openalex.org/W4405306753
fwci
type	preprint
title	Mitigating Out-of-Entity Errors in Named Entity Recognition: A Sentence-Level Strategy
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T10028
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9987999796867371
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1702
topics[0].subfield.display_name	Artificial Intelligence
topics[0].display_name	Topic Modeling
topics[1].id	https://openalex.org/T10181
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9955999851226807
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1702
topics[1].subfield.display_name	Artificial Intelligence
topics[1].display_name	Natural Language Processing Techniques
topics[2].id	https://openalex.org/T13629
topics[2].field.id	https://openalex.org/fields/17
topics[2].field.display_name	Computer Science
topics[2].score	0.9797999858856201
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/1702
topics[2].subfield.display_name	Artificial Intelligence
topics[2].display_name	Text Readability and Simplification
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C2779135771
concepts[0].level	3
concepts[0].score	0.7442044019699097
concepts[0].wikidata	https://www.wikidata.org/wiki/Q403574
concepts[0].display_name	Named-entity recognition
concepts[1].id	https://openalex.org/C96711827
concepts[1].level	3
concepts[1].score	0.6453449726104736
concepts[1].wikidata	https://www.wikidata.org/wiki/Q17012245
concepts[1].display_name	Entity linking
concepts[2].id	https://openalex.org/C41008148
concepts[2].level	0
concepts[2].score	0.6230002045631409
concepts[2].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[2].display_name	Computer science
concepts[3].id	https://openalex.org/C2777530160
concepts[3].level	2
concepts[3].score	0.5912595987319946
concepts[3].wikidata	https://www.wikidata.org/wiki/Q41796
concepts[3].display_name	Sentence
concepts[4].id	https://openalex.org/C204321447
concepts[4].level	1
concepts[4].score	0.5235271453857422
concepts[4].wikidata	https://www.wikidata.org/wiki/Q30642
concepts[4].display_name	Natural language processing
concepts[5].id	https://openalex.org/C154945302
concepts[5].level	1
concepts[5].score	0.40761709213256836
concepts[5].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[5].display_name	Artificial intelligence
concepts[6].id	https://openalex.org/C28490314
concepts[6].level	1
concepts[6].score	0.3685288727283478
concepts[6].wikidata	https://www.wikidata.org/wiki/Q189436
concepts[6].display_name	Speech recognition
concepts[7].id	https://openalex.org/C127413603
concepts[7].level	0
concepts[7].score	0.10877016186714172
concepts[7].wikidata	https://www.wikidata.org/wiki/Q11023
concepts[7].display_name	Engineering
concepts[8].id	https://openalex.org/C201995342
concepts[8].level	1
concepts[8].score	0.0
concepts[8].wikidata	https://www.wikidata.org/wiki/Q682496
concepts[8].display_name	Systems engineering
concepts[9].id	https://openalex.org/C4554734
concepts[9].level	2
concepts[9].score	0.0
concepts[9].wikidata	https://www.wikidata.org/wiki/Q593744
concepts[9].display_name	Knowledge base
concepts[10].id	https://openalex.org/C2780451532
concepts[10].level	2
concepts[10].score	0.0
concepts[10].wikidata	https://www.wikidata.org/wiki/Q759676
concepts[10].display_name	Task (project management)
keywords[0].id	https://openalex.org/keywords/named-entity-recognition
keywords[0].score	0.7442044019699097
keywords[0].display_name	Named-entity recognition
keywords[1].id	https://openalex.org/keywords/entity-linking
keywords[1].score	0.6453449726104736
keywords[1].display_name	Entity linking
keywords[2].id	https://openalex.org/keywords/computer-science
keywords[2].score	0.6230002045631409
keywords[2].display_name	Computer science
keywords[3].id	https://openalex.org/keywords/sentence
keywords[3].score	0.5912595987319946
keywords[3].display_name	Sentence
keywords[4].id	https://openalex.org/keywords/natural-language-processing
keywords[4].score	0.5235271453857422
keywords[4].display_name	Natural language processing
keywords[5].id	https://openalex.org/keywords/artificial-intelligence
keywords[5].score	0.40761709213256836
keywords[5].display_name	Artificial intelligence
keywords[6].id	https://openalex.org/keywords/speech-recognition
keywords[6].score	0.3685288727283478
keywords[6].display_name	Speech recognition
keywords[7].id	https://openalex.org/keywords/engineering
keywords[7].score	0.10877016186714172
keywords[7].display_name	Engineering
language	en
locations[0].id	pmh:oai:arXiv.org:2412.08434
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2412.08434
locations[0].version	submittedVersion
locations[0].raw_type
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2412.08434
locations[1].id	doi:10.48550/arxiv.2412.08434
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2412.08434
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5109715043
authorships[0].author.orcid	https://orcid.org/0009-0002-3415-4473
authorships[0].author.display_name	Guochao Jiang
authorships[0].author_position	first
authorships[0].raw_author_name	Jiang, Guochao
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5037234614
authorships[1].author.orcid
authorships[1].author.display_name	Ziqin Luo
authorships[1].author_position	middle
authorships[1].raw_author_name	Luo, Ziqin
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5104156897
authorships[2].author.orcid
authorships[2].author.display_name	Chengwei Hu
authorships[2].author_position	middle
authorships[2].raw_author_name	Hu, Chengwei
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5058865385
authorships[3].author.orcid
authorships[3].author.display_name	Zepeng Ding
authorships[3].author_position	middle
authorships[3].raw_author_name	Ding, Zepeng
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5046589466
authorships[4].author.orcid	https://orcid.org/0000-0003-1958-7182
authorships[4].author.display_name	Deqing Yang
authorships[4].author_position	last
authorships[4].raw_author_name	Yang, Deqing
authorships[4].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2412.08434
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Mitigating Out-of-Entity Errors in Named Entity Recognition: A Sentence-Level Strategy
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T10028
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9987999796867371
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1702
primary_topic.subfield.display_name	Artificial Intelligence
primary_topic.display_name	Topic Modeling
related_works	https://openalex.org/W2186562580, https://openalex.org/W3198729192, https://openalex.org/W4255258373, https://openalex.org/W2593907245, https://openalex.org/W3000685722, https://openalex.org/W2520117834, https://openalex.org/W626980589, https://openalex.org/W4313162113, https://openalex.org/W1884363728, https://openalex.org/W4390279576
cited_by_count	1
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	1
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2412.08434
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2412.08434
best_oa_location.version	submittedVersion
best_oa_location.raw_type
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2412.08434
primary_location.id	pmh:oai:arXiv.org:2412.08434
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2412.08434
primary_location.version	submittedVersion
primary_location.raw_type
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2412.08434
publication_date	2024-12-11
publication_year	2024
referenced_works_count	0
abstract_inverted_index.a	49, 90, 108
abstract_inverted_index.1)	73
abstract_inverted_index.2)	93
abstract_inverted_index.It	74
abstract_inverted_index.To	40
abstract_inverted_index.in	18, 29, 44
abstract_inverted_index.it	95
abstract_inverted_index.of	3, 12, 22, 37, 82
abstract_inverted_index.on	101, 124
abstract_inverted_index.to	67, 116
abstract_inverted_index.we	47
abstract_inverted_index.NER	119
abstract_inverted_index.Our	59, 121
abstract_inverted_index.and	104, 112
abstract_inverted_index.due	66
abstract_inverted_index.new	50
abstract_inverted_index.not	27
abstract_inverted_index.our	131
abstract_inverted_index.the	10, 16, 19, 23, 30, 35, 68, 77, 84, 97, 102
abstract_inverted_index.two	70
abstract_inverted_index.Many	0
abstract_inverted_index.five	125
abstract_inverted_index.from	9
abstract_inverted_index.have	26, 128
abstract_inverted_index.set.	92
abstract_inverted_index.some	134
abstract_inverted_index.test	24
abstract_inverted_index.this	45
abstract_inverted_index.with	89
abstract_inverted_index.(NER)	7
abstract_inverted_index.S+NER	60, 132
abstract_inverted_index.Then,	94
abstract_inverted_index.based	100
abstract_inverted_index.first	75
abstract_inverted_index.fully	55
abstract_inverted_index.i.e.,	15
abstract_inverted_index.named	4
abstract_inverted_index.that,	130
abstract_inverted_index.which	33, 54
abstract_inverted_index.(OOE),	14
abstract_inverted_index.S+NER,	53
abstract_inverted_index.better	62, 118
abstract_inverted_index.entity	5, 20
abstract_inverted_index.mainly	65
abstract_inverted_index.models	2
abstract_inverted_index.namely	52
abstract_inverted_index.obtain	117
abstract_inverted_index.paper,	46
abstract_inverted_index.suffer	8
abstract_inverted_index.target	85
abstract_inverted_index.tokens	17
abstract_inverted_index.OOE-NER	42, 63, 136
abstract_inverted_index.context	88
abstract_inverted_index.hinders	34
abstract_inverted_index.improve	41
abstract_inverted_index.method,	115
abstract_inverted_index.model's	80
abstract_inverted_index.models.	137
abstract_inverted_index.pooling	114
abstract_inverted_index.problem	11
abstract_inverted_index.propose	48
abstract_inverted_index.refines	96
abstract_inverted_index.samples	25
abstract_inverted_index.through	107
abstract_inverted_index.achieves	61
abstract_inverted_index.appeared	28
abstract_inverted_index.datasets	127
abstract_inverted_index.designs.	72
abstract_inverted_index.entity's	86
abstract_inverted_index.exploits	76
abstract_inverted_index.language	79
abstract_inverted_index.learning	110
abstract_inverted_index.mentions	21
abstract_inverted_index.negative	105
abstract_inverted_index.positive	103
abstract_inverted_index.previous	1
abstract_inverted_index.results.	120
abstract_inverted_index.samples,	32
abstract_inverted_index.strategy	111
abstract_inverted_index.template	91, 113
abstract_inverted_index.training	31
abstract_inverted_index.benchmark	126
abstract_inverted_index.extensive	122
abstract_inverted_index.following	69
abstract_inverted_index.leverages	56
abstract_inverted_index.capability	81
abstract_inverted_index.framework,	51
abstract_inverted_index.particular	71
abstract_inverted_index.templates,	106
abstract_inverted_index.achievement	36
abstract_inverted_index.contrastive	109
abstract_inverted_index.experiments	123
abstract_inverted_index.outperforms	133
abstract_inverted_index.performance	64
abstract_inverted_index.pre-trained	78
abstract_inverted_index.recognition	6
abstract_inverted_index.demonstrated	129
abstract_inverted_index.information.	58
abstract_inverted_index.performance,	43
abstract_inverted_index.performance.	39
abstract_inverted_index.satisfactory	38
abstract_inverted_index.Out-of-Entity	13
abstract_inverted_index.understanding	83
abstract_inverted_index.representation	99
abstract_inverted_index.sentence-level	57, 87, 98
abstract_inverted_index.state-of-the-art	135
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	5
citation_normalized_percentile