Long Document Summarization in a Low Resource Setting using Pretrained Language Models Article Swipe
Ahsaas Bajaj
,
Pavitra Dangati
,
Kalpesh Krishna
,
Pradhiksha Ashok Kumar
,
Rheeya Uppaal
,
Bradford Windsor
,
Eliot Brenner
,
Dominic Dotterrer
,
Rajarshi Das
,
Andrew McCallum
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.18653/v1/2021.acl-srw.7
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.18653/v1/2021.acl-srw.7
ive summarization is the task of compressing a long document into a coherent short document while retaining salient information. Modern abstractive summarization methods are based on deep neural networks which often require large training datasets. Since collecting summarization datasets is an expensive and time-consuming task, practical industrial settings are usually low-resource. In this paper, we study a challenging low-resource setting of summarizing long legal briefs with an average source document length of 4268 words and only 120 available (document, summary) pairs. To account for data scarcity, we used a modern pretrained abstractive summarizer BART (Lewis et al., 2020), which only achieves 17.9 ROUGE-L as it struggles with long documents. We thus attempt to compress these long documents by identifying salient sentences in the source which best ground the summary, using a novel algorithm based on GPT-2 (Radford et al., 2019) language model perplexity scores, that operates within the low resource regime. On feeding the compressed documents to BART, we observe a 6.0 ROUGE-L improvement. Our method also beats several competitive salience detection baselines. Furthermore, the identified salient sentences tend to agree with an independent human labeling by domain experts.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.18653/v1/2021.acl-srw.7
- https://aclanthology.org/2021.acl-srw.7.pdf
- OA Status
- gold
- Cited By
- 3
- Related Works
- 20
- OpenAlex ID
- https://openalex.org/W3152075273
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3152075273Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.18653/v1/2021.acl-srw.7Digital Object Identifier
- Title
-
Long Document Summarization in a Low Resource Setting using Pretrained Language ModelsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-01-01Full publication date if available
- Authors
-
Ahsaas Bajaj, Pavitra Dangati, Kalpesh Krishna, Pradhiksha Ashok Kumar, Rheeya Uppaal, Bradford Windsor, Eliot Brenner, Dominic Dotterrer, Rajarshi Das, Andrew McCallumList of authors in order
- Landing page
-
https://doi.org/10.18653/v1/2021.acl-srw.7Publisher landing page
- PDF URL
-
https://aclanthology.org/2021.acl-srw.7.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://aclanthology.org/2021.acl-srw.7.pdfDirect OA link when available
- Concepts
-
Automatic summarization, Computer science, Salience (neuroscience), Salient, Perplexity, Natural language processing, Artificial intelligence, Task (project management), Language model, Resource (disambiguation), Economics, Computer network, ManagementTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
3Total citation count in OpenAlex
- Citations by year (recent)
-
2023: 2, 2022: 1Per-year citation counts (last 5 years)
- Related works (count)
-
20Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3152075273 |
|---|---|
| doi | https://doi.org/10.18653/v1/2021.acl-srw.7 |
| ids.doi | https://doi.org/10.18653/v1/2021.acl-srw.7 |
| ids.mag | 3152075273 |
| ids.openalex | https://openalex.org/W3152075273 |
| fwci | 0.42331073 |
| type | preprint |
| title | Long Document Summarization in a Low Resource Setting using Pretrained 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 | 0.9071730375289917 |
| 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 | 0.7816903591156006 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C108154423 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6809548735618591 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1469792 |
| concepts[2].display_name | Salience (neuroscience) |
| concepts[3].id | https://openalex.org/C2780719617 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6707972288131714 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1030752 |
| concepts[3].display_name | Salient |
| concepts[4].id | https://openalex.org/C100279451 |
| concepts[4].level | 3 |
| concepts[4].score | 0.6641383767127991 |
| 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 | 0.6230113506317139 |
| 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 | 0.6080866456031799 |
| 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 | 0.4933289587497711 |
| 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 | 0.48392754793167114 |
| 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 | 0.43532615900039673 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q20380951 |
| concepts[9].display_name | Resource (disambiguation) |
| concepts[10].id | https://openalex.org/C162324750 |
| concepts[10].level | 0 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[10].display_name | Economics |
| concepts[11].id | https://openalex.org/C31258907 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q1301371 |
| concepts[11].display_name | Computer network |
| concepts[12].id | https://openalex.org/C187736073 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q2920921 |
| concepts[12].display_name | Management |
| keywords[0].id | https://openalex.org/keywords/automatic-summarization |
| keywords[0].score | 0.9071730375289917 |
| keywords[0].display_name | Automatic summarization |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.7816903591156006 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/salience |
| keywords[2].score | 0.6809548735618591 |
| keywords[2].display_name | Salience (neuroscience) |
| keywords[3].id | https://openalex.org/keywords/salient |
| keywords[3].score | 0.6707972288131714 |
| keywords[3].display_name | Salient |
| keywords[4].id | https://openalex.org/keywords/perplexity |
| keywords[4].score | 0.6641383767127991 |
| keywords[4].display_name | Perplexity |
| keywords[5].id | https://openalex.org/keywords/natural-language-processing |
| keywords[5].score | 0.6230113506317139 |
| keywords[5].display_name | Natural language processing |
| keywords[6].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[6].score | 0.6080866456031799 |
| keywords[6].display_name | Artificial intelligence |
| keywords[7].id | https://openalex.org/keywords/task |
| keywords[7].score | 0.4933289587497711 |
| keywords[7].display_name | Task (project management) |
| keywords[8].id | https://openalex.org/keywords/language-model |
| keywords[8].score | 0.48392754793167114 |
| keywords[8].display_name | Language model |
| keywords[9].id | https://openalex.org/keywords/resource |
| keywords[9].score | 0.43532615900039673 |
| keywords[9].display_name | Resource (disambiguation) |
| language | en |
| locations[0].id | doi:10.18653/v1/2021.acl-srw.7 |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://aclanthology.org/2021.acl-srw.7.pdf |
| locations[0].version | publishedVersion |
| locations[0].raw_type | proceedings-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop |
| locations[0].landing_page_url | https://doi.org/10.18653/v1/2021.acl-srw.7 |
| locations[1].id | pmh:oai:arXiv.org:2103.00751 |
| 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 | https://arxiv.org/pdf/2103.00751 |
| locations[1].version | submittedVersion |
| locations[1].raw_type | |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | http://arxiv.org/abs/2103.00751 |
| locations[2].id | mag:3152075273 |
| locations[2].is_oa | True |
| locations[2].source.id | https://openalex.org/S4306400194 |
| locations[2].source.issn | |
| locations[2].source.type | repository |
| locations[2].source.is_oa | True |
| locations[2].source.issn_l | |
| locations[2].source.is_core | False |
| locations[2].source.is_in_doaj | False |
| locations[2].source.display_name | arXiv (Cornell University) |
| locations[2].source.host_organization | https://openalex.org/I205783295 |
| locations[2].source.host_organization_name | Cornell University |
| locations[2].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[2].license | |
| locations[2].pdf_url | |
| locations[2].version | submittedVersion |
| locations[2].raw_type | |
| locations[2].license_id | |
| locations[2].is_accepted | False |
| locations[2].is_published | False |
| locations[2].raw_source_name | arXiv (Cornell University) |
| locations[2].landing_page_url | http://ui.adsabs.harvard.edu/abs/2021arXiv210300751B/abstract |
| locations[3].id | doi:10.48550/arxiv.2103.00751 |
| locations[3].is_oa | True |
| locations[3].source.id | https://openalex.org/S4306400194 |
| locations[3].source.issn | |
| locations[3].source.type | repository |
| locations[3].source.is_oa | True |
| locations[3].source.issn_l | |
| locations[3].source.is_core | False |
| locations[3].source.is_in_doaj | False |
| locations[3].source.display_name | arXiv (Cornell University) |
| locations[3].source.host_organization | https://openalex.org/I205783295 |
| locations[3].source.host_organization_name | Cornell University |
| locations[3].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[3].license | |
| locations[3].pdf_url | |
| locations[3].version | |
| locations[3].raw_type | article |
| locations[3].license_id | |
| locations[3].is_accepted | False |
| locations[3].is_published | |
| locations[3].raw_source_name | |
| locations[3].landing_page_url | https://doi.org/10.48550/arxiv.2103.00751 |
| indexed_in | arxiv, crossref, datacite |
| authorships[0].author.id | https://openalex.org/A5019300857 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Ahsaas Bajaj |
| authorships[0].countries | KR |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I2250650973 |
| authorships[0].affiliations[0].raw_affiliation_string | Samsung (South Korea), Seoul, South Korea |
| authorships[0].institutions[0].id | https://openalex.org/I2250650973 |
| authorships[0].institutions[0].ror | https://ror.org/04w3jy968 |
| authorships[0].institutions[0].type | company |
| authorships[0].institutions[0].lineage | https://openalex.org/I2250650973 |
| authorships[0].institutions[0].country_code | KR |
| authorships[0].institutions[0].display_name | Samsung (South Korea) |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Ahsaas Bajaj |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Samsung (South Korea), Seoul, South Korea |
| 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 | Pavitra Dangati |
| 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].countries | US |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I24603500 |
| authorships[2].affiliations[0].raw_affiliation_string | University of Massachusetts Amherst, Amherst Center, United States |
| authorships[2].institutions[0].id | https://openalex.org/I24603500 |
| authorships[2].institutions[0].ror | https://ror.org/0072zz521 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I24603500 |
| authorships[2].institutions[0].country_code | US |
| authorships[2].institutions[0].display_name | University of Massachusetts Amherst |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Kalpesh Krishna |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | University of Massachusetts Amherst, Amherst Center, United States |
| 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 | Pradhiksha Ashok Kumar |
| 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].countries | US |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I24603500 |
| authorships[4].affiliations[0].raw_affiliation_string | University of Massachusetts Amherst, Amherst Center, United States |
| authorships[4].institutions[0].id | https://openalex.org/I24603500 |
| authorships[4].institutions[0].ror | https://ror.org/0072zz521 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I24603500 |
| authorships[4].institutions[0].country_code | US |
| authorships[4].institutions[0].display_name | University of Massachusetts Amherst |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Rheeya Uppaal |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | University of Massachusetts Amherst, Amherst Center, United States |
| 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 | Bradford Windsor |
| 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].countries | US |
| authorships[6].affiliations[0].institution_ids | https://openalex.org/I36672615 |
| authorships[6].affiliations[0].raw_affiliation_string | Courant Institute of Mathematical Sciences, New York, United States |
| authorships[6].institutions[0].id | https://openalex.org/I36672615 |
| authorships[6].institutions[0].ror | https://ror.org/037tm7f56 |
| authorships[6].institutions[0].type | education |
| authorships[6].institutions[0].lineage | https://openalex.org/I36672615, https://openalex.org/I57206974 |
| authorships[6].institutions[0].country_code | US |
| authorships[6].institutions[0].display_name | Courant Institute of Mathematical Sciences |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Eliot Brenner |
| authorships[6].is_corresponding | False |
| authorships[6].raw_affiliation_strings | Courant Institute of Mathematical Sciences, New York, United States |
| authorships[7].author.id | https://openalex.org/A5008086932 |
| authorships[7].author.orcid | |
| authorships[7].author.display_name | Dominic Dotterrer |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Dominic Dotterrer |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5106307747 |
| authorships[8].author.orcid | |
| authorships[8].author.display_name | Rajarshi Das |
| authorships[8].countries | US |
| authorships[8].affiliations[0].institution_ids | https://openalex.org/I24603500 |
| authorships[8].affiliations[0].raw_affiliation_string | University of Massachusetts Amherst, Amherst Center, United States |
| authorships[8].institutions[0].id | https://openalex.org/I24603500 |
| authorships[8].institutions[0].ror | https://ror.org/0072zz521 |
| authorships[8].institutions[0].type | education |
| authorships[8].institutions[0].lineage | https://openalex.org/I24603500 |
| authorships[8].institutions[0].country_code | US |
| authorships[8].institutions[0].display_name | University of Massachusetts Amherst |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Rajarshi Das |
| authorships[8].is_corresponding | False |
| authorships[8].raw_affiliation_strings | University of Massachusetts Amherst, Amherst Center, United States |
| authorships[9].author.id | https://openalex.org/A5107835063 |
| authorships[9].author.orcid | |
| authorships[9].author.display_name | Andrew McCallum |
| authorships[9].countries | US |
| authorships[9].affiliations[0].institution_ids | https://openalex.org/I24603500 |
| authorships[9].affiliations[0].raw_affiliation_string | University of Massachusetts Amherst, Amherst Center, United States |
| authorships[9].institutions[0].id | https://openalex.org/I24603500 |
| authorships[9].institutions[0].ror | https://ror.org/0072zz521 |
| authorships[9].institutions[0].type | education |
| authorships[9].institutions[0].lineage | https://openalex.org/I24603500 |
| authorships[9].institutions[0].country_code | US |
| authorships[9].institutions[0].display_name | University of Massachusetts Amherst |
| authorships[9].author_position | last |
| authorships[9].raw_author_name | Andrew McCallum |
| authorships[9].is_corresponding | False |
| authorships[9].raw_affiliation_strings | University of Massachusetts Amherst, Amherst Center, United States |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://aclanthology.org/2021.acl-srw.7.pdf |
| open_access.oa_status | gold |
| 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 Language Models |
| has_fulltext | True |
| 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/W3186252291, https://openalex.org/W3093960175, https://openalex.org/W3133165214, https://openalex.org/W3095287326, https://openalex.org/W3098960752, https://openalex.org/W3094090968, https://openalex.org/W3139403840, https://openalex.org/W3025777352, https://openalex.org/W2966118557, https://openalex.org/W2971289520, https://openalex.org/W2962965405, https://openalex.org/W2983771799, https://openalex.org/W2996264288, https://openalex.org/W2944244173, https://openalex.org/W3200639615, https://openalex.org/W3035643691, https://openalex.org/W3201255524, https://openalex.org/W2997224131, https://openalex.org/W2970465794, https://openalex.org/W3124296283 |
| cited_by_count | 3 |
| counts_by_year[0].year | 2023 |
| counts_by_year[0].cited_by_count | 2 |
| counts_by_year[1].year | 2022 |
| counts_by_year[1].cited_by_count | 1 |
| locations_count | 4 |
| best_oa_location.id | doi:10.18653/v1/2021.acl-srw.7 |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://aclanthology.org/2021.acl-srw.7.pdf |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | proceedings-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop |
| best_oa_location.landing_page_url | https://doi.org/10.18653/v1/2021.acl-srw.7 |
| primary_location.id | doi:10.18653/v1/2021.acl-srw.7 |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://aclanthology.org/2021.acl-srw.7.pdf |
| primary_location.version | publishedVersion |
| primary_location.raw_type | proceedings-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop |
| primary_location.landing_page_url | https://doi.org/10.18653/v1/2021.acl-srw.7 |
| publication_date | 2021-01-01 |
| publication_year | 2021 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 7, 11, 56, 88, 130, 160 |
| abstract_inverted_index.In | 51 |
| abstract_inverted_index.On | 151 |
| abstract_inverted_index.To | 81 |
| abstract_inverted_index.We | 109 |
| abstract_inverted_index.an | 40, 66, 182 |
| abstract_inverted_index.as | 103 |
| abstract_inverted_index.by | 117, 186 |
| abstract_inverted_index.et | 95, 137 |
| abstract_inverted_index.in | 121 |
| abstract_inverted_index.is | 2, 39 |
| abstract_inverted_index.it | 104 |
| abstract_inverted_index.of | 5, 60, 71 |
| abstract_inverted_index.on | 25, 134 |
| abstract_inverted_index.to | 112, 156, 179 |
| abstract_inverted_index.we | 54, 86, 158 |
| abstract_inverted_index.120 | 76 |
| abstract_inverted_index.6.0 | 161 |
| abstract_inverted_index.Our | 164 |
| abstract_inverted_index.and | 42, 74 |
| abstract_inverted_index.are | 23, 48 |
| abstract_inverted_index.for | 83 |
| abstract_inverted_index.low | 148 |
| abstract_inverted_index.the | 3, 122, 127, 147, 153, 174 |
| abstract_inverted_index.17.9 | 101 |
| abstract_inverted_index.4268 | 72 |
| abstract_inverted_index.BART | 93 |
| abstract_inverted_index.al., | 96, 138 |
| abstract_inverted_index.also | 166 |
| abstract_inverted_index.best | 125 |
| abstract_inverted_index.data | 84 |
| abstract_inverted_index.deep | 26 |
| abstract_inverted_index.into | 10 |
| abstract_inverted_index.long | 8, 62, 107, 115 |
| abstract_inverted_index.only | 75, 99 |
| abstract_inverted_index.task | 4 |
| abstract_inverted_index.tend | 178 |
| abstract_inverted_index.that | 144 |
| abstract_inverted_index.this | 52 |
| abstract_inverted_index.thus | 110 |
| abstract_inverted_index.used | 87 |
| abstract_inverted_index.with | 65, 106, 181 |
| abstract_inverted_index.2019) | 139 |
| abstract_inverted_index.BART, | 157 |
| abstract_inverted_index.GPT-2 | 135 |
| abstract_inverted_index.Since | 35 |
| abstract_inverted_index.agree | 180 |
| abstract_inverted_index.based | 24, 133 |
| abstract_inverted_index.beats | 167 |
| abstract_inverted_index.human | 184 |
| abstract_inverted_index.large | 32 |
| abstract_inverted_index.legal | 63 |
| abstract_inverted_index.model | 141 |
| abstract_inverted_index.novel | 131 |
| abstract_inverted_index.often | 30 |
| abstract_inverted_index.short | 13 |
| abstract_inverted_index.study | 55 |
| abstract_inverted_index.task, | 44 |
| abstract_inverted_index.these | 114 |
| abstract_inverted_index.using | 129 |
| abstract_inverted_index.which | 29, 98, 124 |
| abstract_inverted_index.while | 15 |
| abstract_inverted_index.words | 73 |
| abstract_inverted_index.(Lewis | 94 |
| abstract_inverted_index.2020), | 97 |
| abstract_inverted_index.Modern | 19 |
| abstract_inverted_index.briefs | 64 |
| abstract_inverted_index.domain | 187 |
| abstract_inverted_index.ground | 126 |
| abstract_inverted_index.length | 70 |
| abstract_inverted_index.method | 165 |
| abstract_inverted_index.modern | 89 |
| abstract_inverted_index.neural | 27 |
| abstract_inverted_index.pairs. | 80 |
| abstract_inverted_index.paper, | 53 |
| abstract_inverted_index.source | 68, 123 |
| abstract_inverted_index.within | 146 |
| abstract_inverted_index.ROUGE-L | 102, 162 |
| abstract_inverted_index.account | 82 |
| abstract_inverted_index.attempt | 111 |
| abstract_inverted_index.average | 67 |
| abstract_inverted_index.feeding | 152 |
| abstract_inverted_index.methods | 22 |
| abstract_inverted_index.observe | 159 |
| abstract_inverted_index.regime. | 150 |
| abstract_inverted_index.require | 31 |
| abstract_inverted_index.salient | 17, 119, 176 |
| abstract_inverted_index.scores, | 143 |
| abstract_inverted_index.setting | 59 |
| abstract_inverted_index.several | 168 |
| abstract_inverted_index.usually | 49 |
| abstract_inverted_index.(Radford | 136 |
| abstract_inverted_index.achieves | 100 |
| abstract_inverted_index.coherent | 12 |
| abstract_inverted_index.compress | 113 |
| abstract_inverted_index.datasets | 38 |
| abstract_inverted_index.document | 9, 14, 69 |
| abstract_inverted_index.experts. | 188 |
| abstract_inverted_index.labeling | 185 |
| abstract_inverted_index.language | 140 |
| abstract_inverted_index.networks | 28 |
| abstract_inverted_index.operates | 145 |
| abstract_inverted_index.resource | 149 |
| abstract_inverted_index.salience | 170 |
| abstract_inverted_index.settings | 47 |
| abstract_inverted_index.summary) | 79 |
| abstract_inverted_index.summary, | 128 |
| abstract_inverted_index.training | 33 |
| abstract_inverted_index.algorithm | 132 |
| abstract_inverted_index.available | 77 |
| abstract_inverted_index.datasets. | 34 |
| abstract_inverted_index.detection | 171 |
| abstract_inverted_index.documents | 116, 155 |
| abstract_inverted_index.expensive | 41 |
| abstract_inverted_index.practical | 45 |
| abstract_inverted_index.retaining | 16 |
| abstract_inverted_index.scarcity, | 85 |
| abstract_inverted_index.sentences | 120, 177 |
| abstract_inverted_index.struggles | 105 |
| abstract_inverted_index.(document, | 78 |
| abstract_inverted_index.baselines. | 172 |
| abstract_inverted_index.collecting | 36 |
| abstract_inverted_index.compressed | 154 |
| abstract_inverted_index.documents. | 108 |
| abstract_inverted_index.identified | 175 |
| abstract_inverted_index.industrial | 46 |
| abstract_inverted_index.perplexity | 142 |
| abstract_inverted_index.pretrained | 90 |
| abstract_inverted_index.summarizer | 92 |
| abstract_inverted_index.Abstractive | 0 |
| abstract_inverted_index.abstractive | 20, 91 |
| abstract_inverted_index.challenging | 57 |
| abstract_inverted_index.competitive | 169 |
| abstract_inverted_index.compressing | 6 |
| abstract_inverted_index.identifying | 118 |
| abstract_inverted_index.independent | 183 |
| abstract_inverted_index.summarizing | 61 |
| abstract_inverted_index.Furthermore, | 173 |
| abstract_inverted_index.improvement. | 163 |
| abstract_inverted_index.information. | 18 |
| abstract_inverted_index.low-resource | 58 |
| abstract_inverted_index.low-resource. | 50 |
| abstract_inverted_index.summarization | 1, 21, 37 |
| abstract_inverted_index.time-consuming | 43 |
| cited_by_percentile_year.max | 96 |
| cited_by_percentile_year.min | 89 |
| countries_distinct_count | 2 |
| 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 | 0.68017318 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |