Robust PDF Document Conversion using Recurrent Neural Networks Article Swipe
Nikolaos Livathinos
,
Cèsar Berrospi
,
Maksym Lysak
,
Viktor Kuropiatnyk
,
Ahmed Nassar
,
André C. P. L. F. de Carvalho
,
Michele Dolfi
,
Christoph Auer
,
Kasper Dinkla
,
Peter Staar
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.1609/aaai.v35i17.17777
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.1609/aaai.v35i17.17777
The number of published PDF documents in both the academic and commercial world has increased exponentially in recent decades. There is a growing need to make their rich content discoverable to information retrieval tools. Achieving high-quality semantic searches demands that a document's structural components such as title, section headers, paragraphs, (nested) lists, tables and figures (including their captions) are properly identified. Unfortunately, the PDF format is known to not conserve such structural information because it simply represents a document as a stream of low-level printing commands, in which one or more characters are placed in a bounding box with a particular styling. In this paper, we present a novel approach to document structure recovery in PDF using recurrent neural networks to process the low-level PDF data representation directly, instead of relying on a visual re-interpretation of the rendered PDF page, as has been proposed in previous literature. We demonstrate how a sequence of PDF printing commands can be used as input into a neural network and how the network can learn to classify each printing command according to its structural function in the page. This approach has three advantages: First, it can distinguish among more fine-grained labels (typically 10-20 labels as opposed to 1-5 with visual methods), which results in a more accurate and detailed document structure resolution. Second, it can take into account the text flow across pages more naturally compared to visual methods because it can concatenate the printing commands of sequential pages. Last, our proposed method needs less memory and it is computationally less expensive than visual methods. This allows us to deploy such models in production environments at a much lower cost. Through extensive architectural search in combination with advanced feature engineering, we were able to implement a model that yields a weighted average F1 score of 97% across 17 distinct structural labels. The best model we achieved is currently served in production environments on our Corpus Conversion Service (CCS), which was presented at KDD18. This model enhances the capabilities of CCS significantly, as it eliminates the need for human annotated label ground-truth for every unseen document layout. This proved particularly useful when applied to a huge corpus of PDF articles related to COVID-19.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.1609/aaai.v35i17.17777
- https://ojs.aaai.org/index.php/AAAI/article/download/17777/17584
- OA Status
- diamond
- Cited By
- 7
- References
- 12
- Related Works
- 20
- OpenAlex ID
- https://openalex.org/W3132612659
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3132612659Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1609/aaai.v35i17.17777Digital Object Identifier
- Title
-
Robust PDF Document Conversion using Recurrent Neural NetworksWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-05-18Full publication date if available
- Authors
-
Nikolaos Livathinos, Cèsar Berrospi, Maksym Lysak, Viktor Kuropiatnyk, Ahmed Nassar, André C. P. L. F. de Carvalho, Michele Dolfi, Christoph Auer, Kasper Dinkla, Peter StaarList of authors in order
- Landing page
-
https://doi.org/10.1609/aaai.v35i17.17777Publisher landing page
- PDF URL
-
https://ojs.aaai.org/index.php/AAAI/article/download/17777/17584Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
diamondOpen access status per OpenAlex
- OA URL
-
https://ojs.aaai.org/index.php/AAAI/article/download/17777/17584Direct OA link when available
- Concepts
-
Computer science, Representation (politics), Artificial intelligence, Artificial neural network, Feature (linguistics), Process (computing), Function (biology), Information retrieval, Programming language, Political science, Linguistics, Philosophy, Evolutionary biology, Law, Politics, BiologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
7Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1, 2024: 3, 2023: 1, 2022: 2Per-year citation counts (last 5 years)
- References (count)
-
12Number of works referenced by this work
- Related works (count)
-
20Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3132612659 |
|---|---|
| doi | https://doi.org/10.1609/aaai.v35i17.17777 |
| ids.doi | https://doi.org/10.1609/aaai.v35i17.17777 |
| ids.mag | 3132612659 |
| ids.openalex | https://openalex.org/W3132612659 |
| fwci | 2.29473684 |
| type | preprint |
| title | Robust PDF Document Conversion using Recurrent Neural Networks |
| biblio.issue | 17 |
| biblio.volume | 35 |
| biblio.last_page | 15145 |
| biblio.first_page | 15137 |
| topics[0].id | https://openalex.org/T10481 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9904000163078308 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1704 |
| topics[0].subfield.display_name | Computer Graphics and Computer-Aided Design |
| topics[0].display_name | Computer Graphics and Visualization Techniques |
| topics[1].id | https://openalex.org/T10601 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9901999831199646 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Handwritten Text Recognition Techniques |
| topics[2].id | https://openalex.org/T11439 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9830999970436096 |
| 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 | Video Analysis and Summarization |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8108470439910889 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C2776359362 |
| concepts[1].level | 3 |
| concepts[1].score | 0.5907367467880249 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q2145286 |
| concepts[1].display_name | Representation (politics) |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.5145389437675476 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C50644808 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5113041400909424 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[3].display_name | Artificial neural network |
| concepts[4].id | https://openalex.org/C2776401178 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5028249621391296 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q12050496 |
| concepts[4].display_name | Feature (linguistics) |
| concepts[5].id | https://openalex.org/C98045186 |
| concepts[5].level | 2 |
| concepts[5].score | 0.49529948830604553 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q205663 |
| concepts[5].display_name | Process (computing) |
| concepts[6].id | https://openalex.org/C14036430 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4460686445236206 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q3736076 |
| concepts[6].display_name | Function (biology) |
| concepts[7].id | https://openalex.org/C23123220 |
| concepts[7].level | 1 |
| concepts[7].score | 0.3682991862297058 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q816826 |
| concepts[7].display_name | Information retrieval |
| concepts[8].id | https://openalex.org/C199360897 |
| concepts[8].level | 1 |
| concepts[8].score | 0.0795387327671051 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[8].display_name | Programming language |
| concepts[9].id | https://openalex.org/C17744445 |
| concepts[9].level | 0 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q36442 |
| concepts[9].display_name | Political science |
| concepts[10].id | https://openalex.org/C41895202 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[10].display_name | Linguistics |
| concepts[11].id | https://openalex.org/C138885662 |
| concepts[11].level | 0 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[11].display_name | Philosophy |
| concepts[12].id | https://openalex.org/C78458016 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q840400 |
| concepts[12].display_name | Evolutionary biology |
| concepts[13].id | https://openalex.org/C199539241 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q7748 |
| concepts[13].display_name | Law |
| concepts[14].id | https://openalex.org/C94625758 |
| concepts[14].level | 2 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q7163 |
| concepts[14].display_name | Politics |
| concepts[15].id | https://openalex.org/C86803240 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[15].display_name | Biology |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8108470439910889 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/representation |
| keywords[1].score | 0.5907367467880249 |
| keywords[1].display_name | Representation (politics) |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.5145389437675476 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[3].score | 0.5113041400909424 |
| keywords[3].display_name | Artificial neural network |
| keywords[4].id | https://openalex.org/keywords/feature |
| keywords[4].score | 0.5028249621391296 |
| keywords[4].display_name | Feature (linguistics) |
| keywords[5].id | https://openalex.org/keywords/process |
| keywords[5].score | 0.49529948830604553 |
| keywords[5].display_name | Process (computing) |
| keywords[6].id | https://openalex.org/keywords/function |
| keywords[6].score | 0.4460686445236206 |
| keywords[6].display_name | Function (biology) |
| keywords[7].id | https://openalex.org/keywords/information-retrieval |
| keywords[7].score | 0.3682991862297058 |
| keywords[7].display_name | Information retrieval |
| keywords[8].id | https://openalex.org/keywords/programming-language |
| keywords[8].score | 0.0795387327671051 |
| keywords[8].display_name | Programming language |
| language | en |
| locations[0].id | doi:10.1609/aaai.v35i17.17777 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4210191458 |
| locations[0].source.issn | 2159-5399, 2374-3468 |
| locations[0].source.type | conference |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 2159-5399 |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| locations[0].source.host_organization | https://openalex.org/P4310320058 |
| locations[0].source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310320058 |
| locations[0].source.host_organization_lineage_names | Association for the Advancement of Artificial Intelligence |
| locations[0].license | |
| locations[0].pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/17777/17584 |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| locations[0].landing_page_url | https://doi.org/10.1609/aaai.v35i17.17777 |
| locations[1].id | pmh:oai:arXiv.org:2102.09395 |
| 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/2102.09395 |
| locations[1].version | publishedVersion |
| locations[1].raw_type | text |
| locations[1].license_id | |
| locations[1].is_accepted | True |
| locations[1].is_published | True |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | http://arxiv.org/abs/2102.09395 |
| locations[2].id | mag:3132612659 |
| 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://export.arxiv.org/pdf/2102.09395 |
| locations[3].id | doi:10.48550/arxiv.2102.09395 |
| 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.2102.09395 |
| indexed_in | arxiv, crossref, datacite |
| authorships[0].author.id | https://openalex.org/A5084933934 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-8513-3491 |
| authorships[0].author.display_name | Nikolaos Livathinos |
| authorships[0].affiliations[0].raw_affiliation_string | IBM research |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Nikolaos Livathinos |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | IBM research |
| authorships[1].author.id | https://openalex.org/A5039997281 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-6435-4586 |
| authorships[1].author.display_name | Cèsar Berrospi |
| authorships[1].affiliations[0].raw_affiliation_string | IBM research |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Cesar Berrospi |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | IBM research |
| authorships[2].author.id | https://openalex.org/A5024178356 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-3723-6960 |
| authorships[2].author.display_name | Maksym Lysak |
| authorships[2].affiliations[0].raw_affiliation_string | IBM research |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Maksym Lysak |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | IBM research |
| authorships[3].author.id | https://openalex.org/A5002632637 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Viktor Kuropiatnyk |
| authorships[3].affiliations[0].raw_affiliation_string | IBM research |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Viktor Kuropiatnyk |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | IBM research |
| authorships[4].author.id | https://openalex.org/A5021157455 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-9468-0822 |
| authorships[4].author.display_name | Ahmed Nassar |
| authorships[4].affiliations[0].raw_affiliation_string | IBM research |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Ahmed Nassar |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | IBM research |
| authorships[5].author.id | https://openalex.org/A5079499583 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-4765-6459 |
| authorships[5].author.display_name | André C. P. L. F. de Carvalho |
| authorships[5].affiliations[0].raw_affiliation_string | IBM research |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Andre Carvalho |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | IBM research |
| authorships[6].author.id | https://openalex.org/A5038675415 |
| authorships[6].author.orcid | https://orcid.org/0000-0001-7216-8505 |
| authorships[6].author.display_name | Michele Dolfi |
| authorships[6].affiliations[0].raw_affiliation_string | IBM research |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Michele Dolfi |
| authorships[6].is_corresponding | False |
| authorships[6].raw_affiliation_strings | IBM research |
| authorships[7].author.id | https://openalex.org/A5046722997 |
| authorships[7].author.orcid | https://orcid.org/0000-0001-5761-0422 |
| authorships[7].author.display_name | Christoph Auer |
| authorships[7].affiliations[0].raw_affiliation_string | IBM research |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Christoph Auer |
| authorships[7].is_corresponding | False |
| authorships[7].raw_affiliation_strings | IBM research |
| authorships[8].author.id | https://openalex.org/A5022287420 |
| authorships[8].author.orcid | https://orcid.org/0000-0003-2092-166X |
| authorships[8].author.display_name | Kasper Dinkla |
| authorships[8].affiliations[0].raw_affiliation_string | IBM research |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Kasper Dinkla |
| authorships[8].is_corresponding | False |
| authorships[8].raw_affiliation_strings | IBM research |
| authorships[9].author.id | https://openalex.org/A5024778597 |
| authorships[9].author.orcid | https://orcid.org/0000-0002-8088-0823 |
| authorships[9].author.display_name | Peter Staar |
| authorships[9].affiliations[0].raw_affiliation_string | IBM research |
| authorships[9].author_position | last |
| authorships[9].raw_author_name | Peter Staar |
| authorships[9].is_corresponding | False |
| authorships[9].raw_affiliation_strings | IBM research |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://ojs.aaai.org/index.php/AAAI/article/download/17777/17584 |
| open_access.oa_status | diamond |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Robust PDF Document Conversion using Recurrent Neural Networks |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10481 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9904000163078308 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1704 |
| primary_topic.subfield.display_name | Computer Graphics and Computer-Aided Design |
| primary_topic.display_name | Computer Graphics and Visualization Techniques |
| related_works | https://openalex.org/W3104180728, https://openalex.org/W3040920819, https://openalex.org/W3114065210, https://openalex.org/W3043363188, https://openalex.org/W2962928665, https://openalex.org/W2963014193, https://openalex.org/W2915601383, https://openalex.org/W2911086437, https://openalex.org/W3146762582, https://openalex.org/W2781934638, https://openalex.org/W2566938295, https://openalex.org/W3017171774, https://openalex.org/W3118722740, https://openalex.org/W2787405681, https://openalex.org/W2797320628, https://openalex.org/W3016340753, https://openalex.org/W3038774312, https://openalex.org/W3016333779, https://openalex.org/W3011090271, https://openalex.org/W94410696 |
| cited_by_count | 7 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 3 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 1 |
| counts_by_year[3].year | 2022 |
| counts_by_year[3].cited_by_count | 2 |
| locations_count | 4 |
| best_oa_location.id | doi:10.1609/aaai.v35i17.17777 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4210191458 |
| best_oa_location.source.issn | 2159-5399, 2374-3468 |
| best_oa_location.source.type | conference |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 2159-5399 |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| best_oa_location.source.host_organization | https://openalex.org/P4310320058 |
| best_oa_location.source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310320058 |
| best_oa_location.source.host_organization_lineage_names | Association for the Advancement of Artificial Intelligence |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/17777/17584 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| best_oa_location.landing_page_url | https://doi.org/10.1609/aaai.v35i17.17777 |
| primary_location.id | doi:10.1609/aaai.v35i17.17777 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4210191458 |
| primary_location.source.issn | 2159-5399, 2374-3468 |
| primary_location.source.type | conference |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 2159-5399 |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| primary_location.source.host_organization | https://openalex.org/P4310320058 |
| primary_location.source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310320058 |
| primary_location.source.host_organization_lineage_names | Association for the Advancement of Artificial Intelligence |
| primary_location.license | |
| primary_location.pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/17777/17584 |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| primary_location.landing_page_url | https://doi.org/10.1609/aaai.v35i17.17777 |
| publication_date | 2021-05-18 |
| publication_year | 2021 |
| referenced_works | https://openalex.org/W2574872930, https://openalex.org/W2296283641, https://openalex.org/W2970971581, https://openalex.org/W2769423117, https://openalex.org/W3004368638, https://openalex.org/W2795424778, https://openalex.org/W4289751790, https://openalex.org/W2969860478, https://openalex.org/W3003711898, https://openalex.org/W2626778328, https://openalex.org/W2963212250, https://openalex.org/W2806076122 |
| referenced_works_count | 12 |
| abstract_inverted_index.a | 21, 40, 77, 80, 95, 99, 107, 132, 150, 162, 210, 272, 291, 295, 359 |
| abstract_inverted_index.17 | 303 |
| abstract_inverted_index.F1 | 298 |
| abstract_inverted_index.In | 102 |
| abstract_inverted_index.We | 147 |
| abstract_inverted_index.as | 45, 79, 140, 159, 200, 337 |
| abstract_inverted_index.at | 271, 327 |
| abstract_inverted_index.be | 157 |
| abstract_inverted_index.in | 6, 16, 86, 94, 114, 144, 181, 209, 268, 280, 315 |
| abstract_inverted_index.is | 20, 65, 254, 312 |
| abstract_inverted_index.it | 74, 190, 219, 236, 253, 338 |
| abstract_inverted_index.of | 2, 82, 129, 135, 152, 242, 300, 334, 362 |
| abstract_inverted_index.on | 131, 318 |
| abstract_inverted_index.or | 89 |
| abstract_inverted_index.to | 24, 30, 67, 110, 120, 171, 177, 202, 232, 264, 289, 358, 366 |
| abstract_inverted_index.us | 263 |
| abstract_inverted_index.we | 105, 286, 310 |
| abstract_inverted_index.1-5 | 203 |
| abstract_inverted_index.97% | 301 |
| abstract_inverted_index.CCS | 335 |
| abstract_inverted_index.PDF | 4, 63, 115, 124, 138, 153, 363 |
| abstract_inverted_index.The | 0, 307 |
| abstract_inverted_index.and | 10, 53, 165, 213, 252 |
| abstract_inverted_index.are | 58, 92 |
| abstract_inverted_index.box | 97 |
| abstract_inverted_index.can | 156, 169, 191, 220, 237 |
| abstract_inverted_index.for | 342, 347 |
| abstract_inverted_index.has | 13, 141, 186 |
| abstract_inverted_index.how | 149, 166 |
| abstract_inverted_index.its | 178 |
| abstract_inverted_index.not | 68 |
| abstract_inverted_index.one | 88 |
| abstract_inverted_index.our | 246, 319 |
| abstract_inverted_index.the | 8, 62, 122, 136, 167, 182, 224, 239, 332, 340 |
| abstract_inverted_index.was | 325 |
| abstract_inverted_index.This | 184, 261, 329, 352 |
| abstract_inverted_index.able | 288 |
| abstract_inverted_index.been | 142 |
| abstract_inverted_index.best | 308 |
| abstract_inverted_index.both | 7 |
| abstract_inverted_index.data | 125 |
| abstract_inverted_index.each | 173 |
| abstract_inverted_index.flow | 226 |
| abstract_inverted_index.huge | 360 |
| abstract_inverted_index.into | 161, 222 |
| abstract_inverted_index.less | 250, 256 |
| abstract_inverted_index.make | 25 |
| abstract_inverted_index.more | 90, 194, 211, 229 |
| abstract_inverted_index.much | 273 |
| abstract_inverted_index.need | 23, 341 |
| abstract_inverted_index.rich | 27 |
| abstract_inverted_index.such | 44, 70, 266 |
| abstract_inverted_index.take | 221 |
| abstract_inverted_index.text | 225 |
| abstract_inverted_index.than | 258 |
| abstract_inverted_index.that | 39, 293 |
| abstract_inverted_index.this | 103 |
| abstract_inverted_index.used | 158 |
| abstract_inverted_index.were | 287 |
| abstract_inverted_index.when | 356 |
| abstract_inverted_index.with | 98, 204, 282 |
| abstract_inverted_index.10-20 | 198 |
| abstract_inverted_index.Last, | 245 |
| abstract_inverted_index.There | 19 |
| abstract_inverted_index.among | 193 |
| abstract_inverted_index.cost. | 275 |
| abstract_inverted_index.every | 348 |
| abstract_inverted_index.human | 343 |
| abstract_inverted_index.input | 160 |
| abstract_inverted_index.known | 66 |
| abstract_inverted_index.label | 345 |
| abstract_inverted_index.learn | 170 |
| abstract_inverted_index.lower | 274 |
| abstract_inverted_index.model | 292, 309, 330 |
| abstract_inverted_index.needs | 249 |
| abstract_inverted_index.novel | 108 |
| abstract_inverted_index.page, | 139 |
| abstract_inverted_index.page. | 183 |
| abstract_inverted_index.pages | 228 |
| abstract_inverted_index.score | 299 |
| abstract_inverted_index.their | 26, 56 |
| abstract_inverted_index.three | 187 |
| abstract_inverted_index.using | 116 |
| abstract_inverted_index.which | 87, 207, 324 |
| abstract_inverted_index.world | 12 |
| abstract_inverted_index.(CCS), | 323 |
| abstract_inverted_index.Corpus | 320 |
| abstract_inverted_index.First, | 189 |
| abstract_inverted_index.KDD18. | 328 |
| abstract_inverted_index.across | 227, 302 |
| abstract_inverted_index.allows | 262 |
| abstract_inverted_index.corpus | 361 |
| abstract_inverted_index.deploy | 265 |
| abstract_inverted_index.format | 64 |
| abstract_inverted_index.labels | 196, 199 |
| abstract_inverted_index.lists, | 51 |
| abstract_inverted_index.memory | 251 |
| abstract_inverted_index.method | 248 |
| abstract_inverted_index.models | 267 |
| abstract_inverted_index.neural | 118, 163 |
| abstract_inverted_index.number | 1 |
| abstract_inverted_index.pages. | 244 |
| abstract_inverted_index.paper, | 104 |
| abstract_inverted_index.placed | 93 |
| abstract_inverted_index.proved | 353 |
| abstract_inverted_index.recent | 17 |
| abstract_inverted_index.search | 279 |
| abstract_inverted_index.served | 314 |
| abstract_inverted_index.simply | 75 |
| abstract_inverted_index.stream | 81 |
| abstract_inverted_index.tables | 52 |
| abstract_inverted_index.title, | 46 |
| abstract_inverted_index.tools. | 33 |
| abstract_inverted_index.unseen | 349 |
| abstract_inverted_index.useful | 355 |
| abstract_inverted_index.visual | 133, 205, 233, 259 |
| abstract_inverted_index.yields | 294 |
| abstract_inverted_index.Second, | 218 |
| abstract_inverted_index.Service | 322 |
| abstract_inverted_index.Through | 276 |
| abstract_inverted_index.account | 223 |
| abstract_inverted_index.applied | 357 |
| abstract_inverted_index.average | 297 |
| abstract_inverted_index.because | 73, 235 |
| abstract_inverted_index.command | 175 |
| abstract_inverted_index.content | 28 |
| abstract_inverted_index.demands | 38 |
| abstract_inverted_index.feature | 284 |
| abstract_inverted_index.figures | 54 |
| abstract_inverted_index.growing | 22 |
| abstract_inverted_index.instead | 128 |
| abstract_inverted_index.labels. | 306 |
| abstract_inverted_index.layout. | 351 |
| abstract_inverted_index.methods | 234 |
| abstract_inverted_index.network | 164, 168 |
| abstract_inverted_index.opposed | 201 |
| abstract_inverted_index.present | 106 |
| abstract_inverted_index.process | 121 |
| abstract_inverted_index.related | 365 |
| abstract_inverted_index.relying | 130 |
| abstract_inverted_index.results | 208 |
| abstract_inverted_index.section | 47 |
| abstract_inverted_index.(nested) | 50 |
| abstract_inverted_index.academic | 9 |
| abstract_inverted_index.accurate | 212 |
| abstract_inverted_index.achieved | 311 |
| abstract_inverted_index.advanced | 283 |
| abstract_inverted_index.approach | 109, 185 |
| abstract_inverted_index.articles | 364 |
| abstract_inverted_index.bounding | 96 |
| abstract_inverted_index.classify | 172 |
| abstract_inverted_index.commands | 155, 241 |
| abstract_inverted_index.compared | 231 |
| abstract_inverted_index.conserve | 69 |
| abstract_inverted_index.decades. | 18 |
| abstract_inverted_index.detailed | 214 |
| abstract_inverted_index.distinct | 304 |
| abstract_inverted_index.document | 78, 111, 215, 350 |
| abstract_inverted_index.enhances | 331 |
| abstract_inverted_index.function | 180 |
| abstract_inverted_index.headers, | 48 |
| abstract_inverted_index.methods. | 260 |
| abstract_inverted_index.networks | 119 |
| abstract_inverted_index.previous | 145 |
| abstract_inverted_index.printing | 84, 154, 174, 240 |
| abstract_inverted_index.properly | 59 |
| abstract_inverted_index.proposed | 143, 247 |
| abstract_inverted_index.recovery | 113 |
| abstract_inverted_index.rendered | 137 |
| abstract_inverted_index.searches | 37 |
| abstract_inverted_index.semantic | 36 |
| abstract_inverted_index.sequence | 151 |
| abstract_inverted_index.styling. | 101 |
| abstract_inverted_index.weighted | 296 |
| abstract_inverted_index.Achieving | 34 |
| abstract_inverted_index.COVID-19. | 367 |
| abstract_inverted_index.according | 176 |
| abstract_inverted_index.annotated | 344 |
| abstract_inverted_index.captions) | 57 |
| abstract_inverted_index.commands, | 85 |
| abstract_inverted_index.currently | 313 |
| abstract_inverted_index.directly, | 127 |
| abstract_inverted_index.documents | 5 |
| abstract_inverted_index.expensive | 257 |
| abstract_inverted_index.extensive | 277 |
| abstract_inverted_index.implement | 290 |
| abstract_inverted_index.increased | 14 |
| abstract_inverted_index.low-level | 83, 123 |
| abstract_inverted_index.methods), | 206 |
| abstract_inverted_index.naturally | 230 |
| abstract_inverted_index.presented | 326 |
| abstract_inverted_index.published | 3 |
| abstract_inverted_index.recurrent | 117 |
| abstract_inverted_index.retrieval | 32 |
| abstract_inverted_index.structure | 112, 216 |
| abstract_inverted_index.(including | 55 |
| abstract_inverted_index.(typically | 197 |
| abstract_inverted_index.Conversion | 321 |
| abstract_inverted_index.characters | 91 |
| abstract_inverted_index.commercial | 11 |
| abstract_inverted_index.components | 43 |
| abstract_inverted_index.document's | 41 |
| abstract_inverted_index.eliminates | 339 |
| abstract_inverted_index.particular | 100 |
| abstract_inverted_index.production | 269, 316 |
| abstract_inverted_index.represents | 76 |
| abstract_inverted_index.sequential | 243 |
| abstract_inverted_index.structural | 42, 71, 179, 305 |
| abstract_inverted_index.advantages: | 188 |
| abstract_inverted_index.combination | 281 |
| abstract_inverted_index.concatenate | 238 |
| abstract_inverted_index.demonstrate | 148 |
| abstract_inverted_index.distinguish | 192 |
| abstract_inverted_index.identified. | 60 |
| abstract_inverted_index.information | 31, 72 |
| abstract_inverted_index.literature. | 146 |
| abstract_inverted_index.paragraphs, | 49 |
| abstract_inverted_index.resolution. | 217 |
| abstract_inverted_index.capabilities | 333 |
| abstract_inverted_index.discoverable | 29 |
| abstract_inverted_index.engineering, | 285 |
| abstract_inverted_index.environments | 270, 317 |
| abstract_inverted_index.fine-grained | 195 |
| abstract_inverted_index.ground-truth | 346 |
| abstract_inverted_index.high-quality | 35 |
| abstract_inverted_index.particularly | 354 |
| abstract_inverted_index.architectural | 278 |
| abstract_inverted_index.exponentially | 15 |
| abstract_inverted_index.Unfortunately, | 61 |
| abstract_inverted_index.representation | 126 |
| abstract_inverted_index.significantly, | 336 |
| abstract_inverted_index.computationally | 255 |
| abstract_inverted_index.re-interpretation | 134 |
| cited_by_percentile_year.max | 97 |
| cited_by_percentile_year.min | 89 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 10 |
| citation_normalized_percentile.value | 0.93393393 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |