Long Document Summarization in a Low Resource Setting using Pretrained\n Language Models Article Swipe
Ahsaas Bajaj
,
Pavitra Dangati
,
Kalpesh Krishna
,
Pradhiksha Ashok Kumar
,
Rheeya Uppaal
,
Bradford Windsor
,
Eliot Brenner
,
Dominic Dotterrer
,
Raj Das
,
Andrew McCallum
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2103.00751
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2103.00751
ive summarization is the task of compressing a long document into a\ncoherent short document while retaining salient information. Modern abstractive\nsummarization methods are based on deep neural networks which often require\nlarge training datasets. Since collecting summarization datasets is an\nexpensive and time-consuming task, practical industrial settings are usually\nlow-resource. In this paper, we study a challenging low-resource setting of\nsummarizing long legal briefs with an average source document length of 4268\nwords and only 120 available (document, summary) pairs. To account for data\nscarcity, we used a modern pretrained abstractive summarizer BART (Lewis et\nal., 2020), which only achieves 17.9 ROUGE-L as it struggles with long\ndocuments. We thus attempt to compress these long documents by identifying\nsalient sentences in the source which best ground the summary, using a novel\nalgorithm based on GPT-2 (Radford et al., 2019) language model perplexity\nscores, that operates within the low resource regime. On feeding the compressed\ndocuments to BART, we observe a 6.0 ROUGE-L improvement. Our method also beats\nseveral competitive salience detection baselines. Furthermore, the identified\nsalient sentences tend to agree with an independent human labeling by domain\nexperts.\n
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2103.00751
- https://arxiv.org/pdf/2103.00751
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4287322199
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4287322199Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2103.00751Digital Object Identifier
- Title
-
Long Document Summarization in a Low Resource Setting using Pretrained\n Language ModelsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-02-28Full publication date if available
- Authors
-
Ahsaas Bajaj, Pavitra Dangati, Kalpesh Krishna, Pradhiksha Ashok Kumar, Rheeya Uppaal, Bradford Windsor, Eliot Brenner, Dominic Dotterrer, Raj Das, Andrew McCallumList of authors in order
- Landing page
-
https://arxiv.org/abs/2103.00751Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2103.00751Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2103.00751Direct OA link when available
- Concepts
-
Automatic summarization, Computer science, Salient, Salience (neuroscience), Perplexity, Natural language processing, Artificial intelligence, Task (project management), Language model, Resource (disambiguation), Deep learning, Management, Economics, Computer networkTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4287322199 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2103.00751 |
| ids.openalex | https://openalex.org/W4287322199 |
| fwci | 0.0 |
| type | preprint |
| title | Long Document Summarization in a Low Resource Setting using Pretrained\n Language Models |
| 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 | 0.9998000264167786 |
| 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 | 0.9994000196456909 |
| 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/T13083 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9726999998092651 |
| 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 | Advanced Text Analysis Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C170858558 |
| concepts[0].level | 2 |
| concepts[0].score | 0.9080711007118225 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1394144 |
| concepts[0].display_name | Automatic summarization |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.7719699144363403 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C2780719617 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6730716228485107 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1030752 |
| concepts[2].display_name | Salient |
| concepts[3].id | https://openalex.org/C108154423 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6711216568946838 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1469792 |
| concepts[3].display_name | Salience (neuroscience) |
| concepts[4].id | https://openalex.org/C100279451 |
| concepts[4].level | 3 |
| concepts[4].score | 0.6683697700500488 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q372193 |
| concepts[4].display_name | Perplexity |
| concepts[5].id | https://openalex.org/C204321447 |
| concepts[5].level | 1 |
| concepts[5].score | 0.632494330406189 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[5].display_name | Natural language processing |
| concepts[6].id | https://openalex.org/C154945302 |
| concepts[6].level | 1 |
| concepts[6].score | 0.6050458550453186 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[6].display_name | Artificial intelligence |
| concepts[7].id | https://openalex.org/C2780451532 |
| concepts[7].level | 2 |
| concepts[7].score | 0.5062583684921265 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q759676 |
| concepts[7].display_name | Task (project management) |
| concepts[8].id | https://openalex.org/C137293760 |
| concepts[8].level | 2 |
| concepts[8].score | 0.4953416883945465 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q3621696 |
| concepts[8].display_name | Language model |
| concepts[9].id | https://openalex.org/C206345919 |
| concepts[9].level | 2 |
| concepts[9].score | 0.42120233178138733 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q20380951 |
| concepts[9].display_name | Resource (disambiguation) |
| concepts[10].id | https://openalex.org/C108583219 |
| concepts[10].level | 2 |
| concepts[10].score | 0.41388705372810364 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[10].display_name | Deep learning |
| concepts[11].id | https://openalex.org/C187736073 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q2920921 |
| concepts[11].display_name | Management |
| concepts[12].id | https://openalex.org/C162324750 |
| concepts[12].level | 0 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[12].display_name | Economics |
| concepts[13].id | https://openalex.org/C31258907 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q1301371 |
| concepts[13].display_name | Computer network |
| keywords[0].id | https://openalex.org/keywords/automatic-summarization |
| keywords[0].score | 0.9080711007118225 |
| keywords[0].display_name | Automatic summarization |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.7719699144363403 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/salient |
| keywords[2].score | 0.6730716228485107 |
| keywords[2].display_name | Salient |
| keywords[3].id | https://openalex.org/keywords/salience |
| keywords[3].score | 0.6711216568946838 |
| keywords[3].display_name | Salience (neuroscience) |
| keywords[4].id | https://openalex.org/keywords/perplexity |
| keywords[4].score | 0.6683697700500488 |
| keywords[4].display_name | Perplexity |
| keywords[5].id | https://openalex.org/keywords/natural-language-processing |
| keywords[5].score | 0.632494330406189 |
| keywords[5].display_name | Natural language processing |
| keywords[6].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[6].score | 0.6050458550453186 |
| keywords[6].display_name | Artificial intelligence |
| keywords[7].id | https://openalex.org/keywords/task |
| keywords[7].score | 0.5062583684921265 |
| keywords[7].display_name | Task (project management) |
| keywords[8].id | https://openalex.org/keywords/language-model |
| keywords[8].score | 0.4953416883945465 |
| keywords[8].display_name | Language model |
| keywords[9].id | https://openalex.org/keywords/resource |
| keywords[9].score | 0.42120233178138733 |
| keywords[9].display_name | Resource (disambiguation) |
| keywords[10].id | https://openalex.org/keywords/deep-learning |
| keywords[10].score | 0.41388705372810364 |
| keywords[10].display_name | Deep learning |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2103.00751 |
| 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/2103.00751 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| 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/2103.00751 |
| indexed_in | arxiv |
| authorships[0].author.id | https://openalex.org/A5019300857 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Ahsaas Bajaj |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Bajaj, Ahsaas |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5073520830 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Pavitra Dangati |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Dangati, Pavitra |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5078893115 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-6574-0817 |
| authorships[2].author.display_name | Kalpesh Krishna |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Krishna, Kalpesh |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5008742850 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Pradhiksha Ashok Kumar |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Kumar, Pradhiksha Ashok |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5065688288 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-6798-8621 |
| authorships[4].author.display_name | Rheeya Uppaal |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Uppaal, Rheeya |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5002664453 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Bradford Windsor |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Windsor, Bradford |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5082296086 |
| authorships[6].author.orcid | |
| authorships[6].author.display_name | Eliot Brenner |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Brenner, Eliot |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5047345568 |
| authorships[7].author.orcid | |
| authorships[7].author.display_name | Dominic Dotterrer |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Dotterrer, Dominic |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5064600650 |
| authorships[8].author.orcid | https://orcid.org/0000-0001-9977-6201 |
| authorships[8].author.display_name | Raj Das |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Das, Rajarshi |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5107835063 |
| authorships[9].author.orcid | |
| authorships[9].author.display_name | Andrew McCallum |
| authorships[9].author_position | last |
| authorships[9].raw_author_name | McCallum, Andrew |
| authorships[9].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/2103.00751 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Long Document Summarization in a Low Resource Setting using Pretrained\n Language Models |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| 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 | 0.9998000264167786 |
| 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/W4307308932, https://openalex.org/W2323464168, https://openalex.org/W2996124973, https://openalex.org/W2169518243, https://openalex.org/W2089705257, https://openalex.org/W2252095989, https://openalex.org/W4383427356, https://openalex.org/W4235368871, https://openalex.org/W4322096525, https://openalex.org/W2949519365 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | pmh:oai:arXiv.org:2103.00751 |
| 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/2103.00751 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| 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/2103.00751 |
| primary_location.id | pmh:oai:arXiv.org:2103.00751 |
| 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/2103.00751 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| 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/2103.00751 |
| publication_date | 2021-02-28 |
| publication_year | 2021 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 7, 51, 80, 119, 146 |
| abstract_inverted_index.In | 46 |
| abstract_inverted_index.On | 138 |
| abstract_inverted_index.To | 74 |
| abstract_inverted_index.We | 99 |
| abstract_inverted_index.an | 60, 166 |
| abstract_inverted_index.as | 94 |
| abstract_inverted_index.by | 107, 170 |
| abstract_inverted_index.et | 125 |
| abstract_inverted_index.in | 110 |
| abstract_inverted_index.is | 2, 36 |
| abstract_inverted_index.it | 95 |
| abstract_inverted_index.of | 5, 65 |
| abstract_inverted_index.on | 23, 122 |
| abstract_inverted_index.to | 102, 142, 163 |
| abstract_inverted_index.we | 49, 78, 144 |
| abstract_inverted_index.120 | 69 |
| abstract_inverted_index.6.0 | 147 |
| abstract_inverted_index.Our | 150 |
| abstract_inverted_index.and | 38, 67 |
| abstract_inverted_index.are | 21, 44 |
| abstract_inverted_index.for | 76 |
| abstract_inverted_index.low | 135 |
| abstract_inverted_index.the | 3, 111, 116, 134, 140, 159 |
| abstract_inverted_index.17.9 | 92 |
| abstract_inverted_index.BART | 85 |
| abstract_inverted_index.al., | 126 |
| abstract_inverted_index.also | 152 |
| abstract_inverted_index.best | 114 |
| abstract_inverted_index.deep | 24 |
| abstract_inverted_index.into | 10 |
| abstract_inverted_index.long | 8, 56, 105 |
| abstract_inverted_index.only | 68, 90 |
| abstract_inverted_index.task | 4 |
| abstract_inverted_index.tend | 162 |
| abstract_inverted_index.that | 131 |
| abstract_inverted_index.this | 47 |
| abstract_inverted_index.thus | 100 |
| abstract_inverted_index.used | 79 |
| abstract_inverted_index.with | 59, 97, 165 |
| abstract_inverted_index.2019) | 127 |
| abstract_inverted_index.BART, | 143 |
| abstract_inverted_index.GPT-2 | 123 |
| abstract_inverted_index.Since | 32 |
| abstract_inverted_index.agree | 164 |
| abstract_inverted_index.based | 22, 121 |
| abstract_inverted_index.human | 168 |
| abstract_inverted_index.legal | 57 |
| abstract_inverted_index.model | 129 |
| abstract_inverted_index.often | 28 |
| abstract_inverted_index.short | 12 |
| abstract_inverted_index.study | 50 |
| abstract_inverted_index.task, | 40 |
| abstract_inverted_index.these | 104 |
| abstract_inverted_index.using | 118 |
| abstract_inverted_index.which | 27, 89, 113 |
| abstract_inverted_index.while | 14 |
| abstract_inverted_index.(Lewis | 86 |
| abstract_inverted_index.2020), | 88 |
| abstract_inverted_index.Modern | 18 |
| abstract_inverted_index.briefs | 58 |
| abstract_inverted_index.ground | 115 |
| abstract_inverted_index.length | 64 |
| abstract_inverted_index.method | 151 |
| abstract_inverted_index.modern | 81 |
| abstract_inverted_index.neural | 25 |
| abstract_inverted_index.pairs. | 73 |
| abstract_inverted_index.paper, | 48 |
| abstract_inverted_index.source | 62, 112 |
| abstract_inverted_index.within | 133 |
| abstract_inverted_index.ROUGE-L | 93, 148 |
| abstract_inverted_index.account | 75 |
| abstract_inverted_index.attempt | 101 |
| abstract_inverted_index.average | 61 |
| abstract_inverted_index.feeding | 139 |
| abstract_inverted_index.methods | 20 |
| abstract_inverted_index.observe | 145 |
| abstract_inverted_index.regime. | 137 |
| abstract_inverted_index.salient | 16 |
| abstract_inverted_index.setting | 54 |
| abstract_inverted_index.(Radford | 124 |
| abstract_inverted_index.achieves | 91 |
| abstract_inverted_index.compress | 103 |
| abstract_inverted_index.datasets | 35 |
| abstract_inverted_index.document | 9, 13, 63 |
| abstract_inverted_index.et\nal., | 87 |
| abstract_inverted_index.labeling | 169 |
| abstract_inverted_index.language | 128 |
| abstract_inverted_index.networks | 26 |
| abstract_inverted_index.operates | 132 |
| abstract_inverted_index.resource | 136 |
| abstract_inverted_index.salience | 155 |
| abstract_inverted_index.settings | 43 |
| abstract_inverted_index.summary) | 72 |
| abstract_inverted_index.summary, | 117 |
| abstract_inverted_index.training | 30 |
| abstract_inverted_index.available | 70 |
| abstract_inverted_index.datasets. | 31 |
| abstract_inverted_index.detection | 156 |
| abstract_inverted_index.documents | 106 |
| abstract_inverted_index.practical | 41 |
| abstract_inverted_index.retaining | 15 |
| abstract_inverted_index.sentences | 109, 161 |
| abstract_inverted_index.struggles | 96 |
| abstract_inverted_index.(document, | 71 |
| abstract_inverted_index.baselines. | 157 |
| abstract_inverted_index.collecting | 33 |
| abstract_inverted_index.industrial | 42 |
| abstract_inverted_index.pretrained | 82 |
| abstract_inverted_index.summarizer | 84 |
| abstract_inverted_index.4268\nwords | 66 |
| abstract_inverted_index.Abstractive | 0 |
| abstract_inverted_index.a\ncoherent | 11 |
| abstract_inverted_index.abstractive | 83 |
| abstract_inverted_index.challenging | 52 |
| abstract_inverted_index.competitive | 154 |
| abstract_inverted_index.compressing | 6 |
| abstract_inverted_index.independent | 167 |
| abstract_inverted_index.Furthermore, | 158 |
| abstract_inverted_index.improvement. | 149 |
| abstract_inverted_index.information. | 17 |
| abstract_inverted_index.low-resource | 53 |
| abstract_inverted_index.an\nexpensive | 37 |
| abstract_inverted_index.summarization | 1, 34 |
| abstract_inverted_index.beats\nseveral | 153 |
| abstract_inverted_index.require\nlarge | 29 |
| abstract_inverted_index.time-consuming | 39 |
| abstract_inverted_index.data\nscarcity, | 77 |
| abstract_inverted_index.of\nsummarizing | 55 |
| abstract_inverted_index.long\ndocuments. | 98 |
| abstract_inverted_index.novel\nalgorithm | 120 |
| abstract_inverted_index.domain\nexperts.\n | 171 |
| abstract_inverted_index.identified\nsalient | 160 |
| abstract_inverted_index.perplexity\nscores, | 130 |
| abstract_inverted_index.identifying\nsalient | 108 |
| abstract_inverted_index.compressed\ndocuments | 141 |
| abstract_inverted_index.usually\nlow-resource. | 45 |
| abstract_inverted_index.abstractive\nsummarization | 19 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 10 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/8 |
| sustainable_development_goals[0].score | 0.5400000214576721 |
| sustainable_development_goals[0].display_name | Decent work and economic growth |
| citation_normalized_percentile.value | 0.24608275 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |