ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks Article Swipe

PDF

Jiasen Lu , Dhruv Batra , Devi Parikh , Stefan Lee ·

YOU? · · 2019 · Open Access · · DOI: https://doi.org/10.48550/arxiv.1908.02265

We present ViLBERT (short for Vision-and-Language BERT), a model for learning task-agnostic joint representations of image content and natural language. We extend the popular BERT architecture to a multi-modal two-stream model, pro-cessing both visual and textual inputs in separate streams that interact through co-attentional transformer layers. We pretrain our model through two proxy tasks on the large, automatically collected Conceptual Captions dataset and then transfer it to multiple established vision-and-language tasks -- visual question answering, visual commonsense reasoning, referring expressions, and caption-based image retrieval -- by making only minor additions to the base architecture. We observe significant improvements across tasks compared to existing task-specific models -- achieving state-of-the-art on all four tasks. Our work represents a shift away from learning groundings between vision and language only as part of task training and towards treating visual grounding as a pretrainable and transferable capability.

Related Topics

Computer Science

Artificial Intelligence

Transformer

Architecture

Human–Computer Interaction

Concepts

Computer science Commonsense reasoning Natural language processing Artificial intelligence Question answering Task (project management) Transformer Natural language Architecture Multi-task learning Language understanding Natural language understanding Visual reasoning Language model Human–computer interaction Visual arts Art Economics Quantum mechanics Voltage Physics Management

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/1908.02265
PDF: https://arxiv.org/pdf/1908.02265
OA Status: green
Cited By: 1672
References: 30
Related Works: 10
OpenAlex ID: https://openalex.org/W2966715458

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W2966715458

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.1908.02265

Digital Object Identifier
Title: ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2019

Year of publication
Publication date: 2019-08-06

Full publication date if available
Authors: Jiasen Lu, Dhruv Batra, Devi Parikh, Stefan Lee

List of authors in order
Landing page: https://arxiv.org/abs/1908.02265

Publisher landing page
PDF URL: https://arxiv.org/pdf/1908.02265

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/1908.02265

Direct OA link when available
Concepts: Computer science, Commonsense reasoning, Natural language processing, Artificial intelligence, Question answering, Task (project management), Transformer, Natural language, Architecture, Multi-task learning, Language understanding, Natural language understanding, Visual reasoning, Language model, Human–computer interaction, Visual arts, Art, Economics, Quantum mechanics, Voltage, Physics, Management

Top concepts (fields/topics) attached by OpenAlex
Cited by: 1672

Total citation count in OpenAlex
Citations by year (recent): 2025: 150, 2024: 279, 2023: 496, 2022: 392, 2021: 264

Per-year citation counts (last 5 years)
References (count): 30

Number of works referenced by this work
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W2966715458
doi	https://doi.org/10.48550/arxiv.1908.02265
ids.doi	https://doi.org/10.48550/arxiv.1908.02265
ids.mag	2966715458
ids.openalex	https://openalex.org/W2966715458
fwci
type	preprint
title	ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T11714
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	1.0
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1707
topics[0].subfield.display_name	Computer Vision and Pattern Recognition
topics[0].display_name	Multimodal Machine Learning Applications
topics[1].id	https://openalex.org/T11307
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	Domain Adaptation and Few-Shot Learning
topics[2].id	https://openalex.org/T10627
topics[2].field.id	https://openalex.org/fields/17
topics[2].field.display_name	Computer Science
topics[2].score	0.9847000241279602
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/1707
topics[2].subfield.display_name	Computer Vision and Pattern Recognition
topics[2].display_name	Advanced Image and Video Retrieval Techniques
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.8107885122299194
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
concepts[1].id	https://openalex.org/C193221554
concepts[1].level	2
concepts[1].score	0.690273106098175
concepts[1].wikidata	https://www.wikidata.org/wiki/Q5153664
concepts[1].display_name	Commonsense reasoning
concepts[2].id	https://openalex.org/C204321447
concepts[2].level	1
concepts[2].score	0.6208510398864746
concepts[2].wikidata	https://www.wikidata.org/wiki/Q30642
concepts[2].display_name	Natural language processing
concepts[3].id	https://openalex.org/C154945302
concepts[3].level	1
concepts[3].score	0.5618556141853333
concepts[3].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[3].display_name	Artificial intelligence
concepts[4].id	https://openalex.org/C44291984
concepts[4].level	2
concepts[4].score	0.5526125431060791
concepts[4].wikidata	https://www.wikidata.org/wiki/Q1074173
concepts[4].display_name	Question answering
concepts[5].id	https://openalex.org/C2780451532
concepts[5].level	2
concepts[5].score	0.5341948866844177
concepts[5].wikidata	https://www.wikidata.org/wiki/Q759676
concepts[5].display_name	Task (project management)
concepts[6].id	https://openalex.org/C66322947
concepts[6].level	3
concepts[6].score	0.5284464359283447
concepts[6].wikidata	https://www.wikidata.org/wiki/Q11658
concepts[6].display_name	Transformer
concepts[7].id	https://openalex.org/C195324797
concepts[7].level	2
concepts[7].score	0.4826265275478363
concepts[7].wikidata	https://www.wikidata.org/wiki/Q33742
concepts[7].display_name	Natural language
concepts[8].id	https://openalex.org/C123657996
concepts[8].level	2
concepts[8].score	0.4582878649234772
concepts[8].wikidata	https://www.wikidata.org/wiki/Q12271
concepts[8].display_name	Architecture
concepts[9].id	https://openalex.org/C28006648
concepts[9].level	3
concepts[9].score	0.4574020504951477
concepts[9].wikidata	https://www.wikidata.org/wiki/Q6934509
concepts[9].display_name	Multi-task learning
concepts[10].id	https://openalex.org/C2983448237
concepts[10].level	2
concepts[10].score	0.45251891016960144
concepts[10].wikidata	https://www.wikidata.org/wiki/Q1078276
concepts[10].display_name	Language understanding
concepts[11].id	https://openalex.org/C2779439875
concepts[11].level	3
concepts[11].score	0.43654322624206543
concepts[11].wikidata	https://www.wikidata.org/wiki/Q1078276
concepts[11].display_name	Natural language understanding
concepts[12].id	https://openalex.org/C2777508537
concepts[12].level	2
concepts[12].score	0.42785608768463135
concepts[12].wikidata	https://www.wikidata.org/wiki/Q7936620
concepts[12].display_name	Visual reasoning
concepts[13].id	https://openalex.org/C137293760
concepts[13].level	2
concepts[13].score	0.42752042412757874
concepts[13].wikidata	https://www.wikidata.org/wiki/Q3621696
concepts[13].display_name	Language model
concepts[14].id	https://openalex.org/C107457646
concepts[14].level	1
concepts[14].score	0.32127615809440613
concepts[14].wikidata	https://www.wikidata.org/wiki/Q207434
concepts[14].display_name	Human–computer interaction
concepts[15].id	https://openalex.org/C153349607
concepts[15].level	1
concepts[15].score	0.0
concepts[15].wikidata	https://www.wikidata.org/wiki/Q36649
concepts[15].display_name	Visual arts
concepts[16].id	https://openalex.org/C142362112
concepts[16].level	0
concepts[16].score	0.0
concepts[16].wikidata	https://www.wikidata.org/wiki/Q735
concepts[16].display_name	Art
concepts[17].id	https://openalex.org/C162324750
concepts[17].level	0
concepts[17].score	0.0
concepts[17].wikidata	https://www.wikidata.org/wiki/Q8134
concepts[17].display_name	Economics
concepts[18].id	https://openalex.org/C62520636
concepts[18].level	1
concepts[18].score	0.0
concepts[18].wikidata	https://www.wikidata.org/wiki/Q944
concepts[18].display_name	Quantum mechanics
concepts[19].id	https://openalex.org/C165801399
concepts[19].level	2
concepts[19].score	0.0
concepts[19].wikidata	https://www.wikidata.org/wiki/Q25428
concepts[19].display_name	Voltage
concepts[20].id	https://openalex.org/C121332964
concepts[20].level	0
concepts[20].score	0.0
concepts[20].wikidata	https://www.wikidata.org/wiki/Q413
concepts[20].display_name	Physics
concepts[21].id	https://openalex.org/C187736073
concepts[21].level	1
concepts[21].score	0.0
concepts[21].wikidata	https://www.wikidata.org/wiki/Q2920921
concepts[21].display_name	Management
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.8107885122299194
keywords[0].display_name	Computer science
keywords[1].id	https://openalex.org/keywords/commonsense-reasoning
keywords[1].score	0.690273106098175
keywords[1].display_name	Commonsense reasoning
keywords[2].id	https://openalex.org/keywords/natural-language-processing
keywords[2].score	0.6208510398864746
keywords[2].display_name	Natural language processing
keywords[3].id	https://openalex.org/keywords/artificial-intelligence
keywords[3].score	0.5618556141853333
keywords[3].display_name	Artificial intelligence
keywords[4].id	https://openalex.org/keywords/question-answering
keywords[4].score	0.5526125431060791
keywords[4].display_name	Question answering
keywords[5].id	https://openalex.org/keywords/task
keywords[5].score	0.5341948866844177
keywords[5].display_name	Task (project management)
keywords[6].id	https://openalex.org/keywords/transformer
keywords[6].score	0.5284464359283447
keywords[6].display_name	Transformer
keywords[7].id	https://openalex.org/keywords/natural-language
keywords[7].score	0.4826265275478363
keywords[7].display_name	Natural language
keywords[8].id	https://openalex.org/keywords/architecture
keywords[8].score	0.4582878649234772
keywords[8].display_name	Architecture
keywords[9].id	https://openalex.org/keywords/multi-task-learning
keywords[9].score	0.4574020504951477
keywords[9].display_name	Multi-task learning
keywords[10].id	https://openalex.org/keywords/language-understanding
keywords[10].score	0.45251891016960144
keywords[10].display_name	Language understanding
keywords[11].id	https://openalex.org/keywords/natural-language-understanding
keywords[11].score	0.43654322624206543
keywords[11].display_name	Natural language understanding
keywords[12].id	https://openalex.org/keywords/visual-reasoning
keywords[12].score	0.42785608768463135
keywords[12].display_name	Visual reasoning
keywords[13].id	https://openalex.org/keywords/language-model
keywords[13].score	0.42752042412757874
keywords[13].display_name	Language model
keywords[14].id	https://openalex.org/keywords/human–computer-interaction
keywords[14].score	0.32127615809440613
keywords[14].display_name	Human–computer interaction
language	en
locations[0].id	pmh:oai:arXiv.org:1908.02265
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/1908.02265
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/1908.02265
locations[1].id	doi:10.48550/arxiv.1908.02265
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.1908.02265
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5101055775
authorships[0].author.orcid
authorships[0].author.display_name	Jiasen Lu
authorships[0].author_position	first
authorships[0].raw_author_name	Jiasen Lu
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5014035752
authorships[1].author.orcid
authorships[1].author.display_name	Dhruv Batra
authorships[1].author_position	middle
authorships[1].raw_author_name	Dhruv Batra
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5050342343
authorships[2].author.orcid
authorships[2].author.display_name	Devi Parikh
authorships[2].author_position	middle
authorships[2].raw_author_name	Devi Parikh
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5051259505
authorships[3].author.orcid	https://orcid.org/0000-0001-5953-1963
authorships[3].author.display_name	Stefan Lee
authorships[3].author_position	last
authorships[3].raw_author_name	Stefan Lee
authorships[3].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/1908.02265
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2019-08-13T00:00:00
display_name	ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T11714
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	1.0
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1707
primary_topic.subfield.display_name	Computer Vision and Pattern Recognition
primary_topic.display_name	Multimodal Machine Learning Applications
related_works	https://openalex.org/W4389518870, https://openalex.org/W2928107702, https://openalex.org/W4388093383, https://openalex.org/W2621232079, https://openalex.org/W4293519385, https://openalex.org/W3175270222, https://openalex.org/W3180295840, https://openalex.org/W3189094972, https://openalex.org/W4296269439, https://openalex.org/W3187064440
cited_by_count	1672
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	150
counts_by_year[1].year	2024
counts_by_year[1].cited_by_count	279
counts_by_year[2].year	2023
counts_by_year[2].cited_by_count	496
counts_by_year[3].year	2022
counts_by_year[3].cited_by_count	392
counts_by_year[4].year	2021
counts_by_year[4].cited_by_count	264
counts_by_year[5].year	2020
counts_by_year[5].cited_by_count	88
counts_by_year[6].year	2019
counts_by_year[6].cited_by_count	3
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:1908.02265
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/1908.02265
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/1908.02265
primary_location.id	pmh:oai:arXiv.org:1908.02265
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/1908.02265
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/1908.02265
publication_date	2019-08-06
publication_year	2019
referenced_works	https://openalex.org/W2784458614, https://openalex.org/W2626778328, https://openalex.org/W2774005037, https://openalex.org/W3104279398, https://openalex.org/W2611669587, https://openalex.org/W2886641317, https://openalex.org/W2198618282, https://openalex.org/W2599765304, https://openalex.org/W2963800628, https://openalex.org/W2913129712, https://openalex.org/W2745461083, https://openalex.org/W2963245493, https://openalex.org/W2117539524, https://openalex.org/W2185175083, https://openalex.org/W2768661419, https://openalex.org/W343636949, https://openalex.org/W2251512949, https://openalex.org/W2953106684, https://openalex.org/W2798802295, https://openalex.org/W2963341956, https://openalex.org/W2903867219, https://openalex.org/W2144796873, https://openalex.org/W2949891561, https://openalex.org/W2787560479, https://openalex.org/W2525778437, https://openalex.org/W2931316642, https://openalex.org/W2575671312, https://openalex.org/W2194775991, https://openalex.org/W2914120296, https://openalex.org/W1957780744
referenced_works_count	30
abstract_inverted_index.a	7, 27, 115, 137
abstract_inverted_index.--	71, 84, 105
abstract_inverted_index.We	0, 20, 46, 94
abstract_inverted_index.as	126, 136
abstract_inverted_index.by	85
abstract_inverted_index.in	37
abstract_inverted_index.it	65
abstract_inverted_index.of	14, 128
abstract_inverted_index.on	54, 108
abstract_inverted_index.to	26, 66, 90, 101
abstract_inverted_index.Our	112
abstract_inverted_index.all	109
abstract_inverted_index.and	17, 34, 62, 80, 123, 131, 139
abstract_inverted_index.for	4, 9
abstract_inverted_index.our	48
abstract_inverted_index.the	22, 55, 91
abstract_inverted_index.two	51
abstract_inverted_index.BERT	24
abstract_inverted_index.away	117
abstract_inverted_index.base	92
abstract_inverted_index.both	32
abstract_inverted_index.four	110
abstract_inverted_index.from	118
abstract_inverted_index.only	87, 125
abstract_inverted_index.part	127
abstract_inverted_index.task	129
abstract_inverted_index.that	40
abstract_inverted_index.then	63
abstract_inverted_index.work	113
abstract_inverted_index.image	15, 82
abstract_inverted_index.joint	12
abstract_inverted_index.minor	88
abstract_inverted_index.model	8, 49
abstract_inverted_index.proxy	52
abstract_inverted_index.shift	116
abstract_inverted_index.tasks	53, 70, 99
abstract_inverted_index.(short	3
abstract_inverted_index.BERT),	6
abstract_inverted_index.across	98
abstract_inverted_index.extend	21
abstract_inverted_index.inputs	36
abstract_inverted_index.large,	56
abstract_inverted_index.making	86
abstract_inverted_index.model,	30
abstract_inverted_index.models	104
abstract_inverted_index.tasks.	111
abstract_inverted_index.vision	122
abstract_inverted_index.visual	33, 72, 75, 134
abstract_inverted_index.ViLBERT	2
abstract_inverted_index.between	121
abstract_inverted_index.content	16
abstract_inverted_index.dataset	61
abstract_inverted_index.layers.	45
abstract_inverted_index.natural	18
abstract_inverted_index.observe	95
abstract_inverted_index.popular	23
abstract_inverted_index.present	1
abstract_inverted_index.streams	39
abstract_inverted_index.textual	35
abstract_inverted_index.through	42, 50
abstract_inverted_index.towards	132
abstract_inverted_index.Captions	60
abstract_inverted_index.compared	100
abstract_inverted_index.existing	102
abstract_inverted_index.interact	41
abstract_inverted_index.language	124
abstract_inverted_index.learning	10, 119
abstract_inverted_index.multiple	67
abstract_inverted_index.pretrain	47
abstract_inverted_index.question	73
abstract_inverted_index.separate	38
abstract_inverted_index.training	130
abstract_inverted_index.transfer	64
abstract_inverted_index.treating	133
abstract_inverted_index.achieving	106
abstract_inverted_index.additions	89
abstract_inverted_index.collected	58
abstract_inverted_index.grounding	135
abstract_inverted_index.language.	19
abstract_inverted_index.referring	78
abstract_inverted_index.retrieval	83
abstract_inverted_index.Conceptual	59
abstract_inverted_index.answering,	74
abstract_inverted_index.groundings	120
abstract_inverted_index.reasoning,	77
abstract_inverted_index.represents	114
abstract_inverted_index.two-stream	29
abstract_inverted_index.capability.	141
abstract_inverted_index.commonsense	76
abstract_inverted_index.established	68
abstract_inverted_index.multi-modal	28
abstract_inverted_index.pro-cessing	31
abstract_inverted_index.significant	96
abstract_inverted_index.transformer	44
abstract_inverted_index.architecture	25
abstract_inverted_index.expressions,	79
abstract_inverted_index.improvements	97
abstract_inverted_index.pretrainable	138
abstract_inverted_index.transferable	140
abstract_inverted_index.architecture.	93
abstract_inverted_index.automatically	57
abstract_inverted_index.caption-based	81
abstract_inverted_index.task-agnostic	11
abstract_inverted_index.task-specific	103
abstract_inverted_index.co-attentional	43
abstract_inverted_index.representations	13
abstract_inverted_index.state-of-the-art	107
abstract_inverted_index.Vision-and-Language	5
abstract_inverted_index.vision-and-language	69
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	4
sustainable_development_goals[0].id	https://metadata.un.org/sdg/4
sustainable_development_goals[0].score	0.699999988079071
sustainable_development_goals[0].display_name	Quality Education
citation_normalized_percentile