Mask and Reason Article Swipe
Xiao Liu
,
Shiyu Zhao
,
Kai Su
,
Yukuo Cen
,
Jiezhong Qiu
,
Mengdi Zhang
,
Wei Biao Wu
,
Yuxiao Dong
,
Jie Tang
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1145/3534678.3539472
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1145/3534678.3539472
Knowledge graph (KG) embeddings have been a mainstream approach for reasoning\nover incomplete KGs. However, limited by their inherently shallow and static\narchitectures, they can hardly deal with the rising focus on complex logical\nqueries, which comprise logical operators, imputed edges, multiple source\nentities, and unknown intermediate entities. In this work, we present the\nKnowledge Graph Transformer (kgTransformer) with masked pre-training and\nfine-tuning strategies. We design a KG triple transformation method to enable\nTransformer to handle KGs, which is further strengthened by the\nMixture-of-Experts (MoE) sparse activation. We then formulate the complex\nlogical queries as masked prediction and introduce a two-stage masked\npre-training strategy to improve transferability and generalizability.\nExtensive experiments on two benchmarks demonstrate that kgTransformer can\nconsistently outperform both KG embedding-based baselines and advanced encoders\non nine in-domain and out-of-domain reasoning tasks. Additionally,\nkgTransformer can reason with explainability via providing the full reasoning\npaths to interpret given answers.\n
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1145/3534678.3539472
- https://dl.acm.org/doi/pdf/10.1145/3534678.3539472
- OA Status
- bronze
- Cited By
- 35
- References
- 56
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4290944058
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4290944058Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1145/3534678.3539472Digital Object Identifier
- Title
-
Mask and ReasonWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-08-12Full publication date if available
- Authors
-
Xiao Liu, Shiyu Zhao, Kai Su, Yukuo Cen, Jiezhong Qiu, Mengdi Zhang, Wei Biao Wu, Yuxiao Dong, Jie TangList of authors in order
- Landing page
-
https://doi.org/10.1145/3534678.3539472Publisher landing page
- PDF URL
-
https://dl.acm.org/doi/pdf/10.1145/3534678.3539472Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
bronzeOpen access status per OpenAlex
- OA URL
-
https://dl.acm.org/doi/pdf/10.1145/3534678.3539472Direct OA link when available
- Concepts
-
Computer scienceTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
35Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 7, 2024: 16, 2023: 11, 2022: 1Per-year citation counts (last 5 years)
- References (count)
-
56Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4290944058 |
|---|---|
| doi | https://doi.org/10.1145/3534678.3539472 |
| ids.doi | https://doi.org/10.1145/3534678.3539472 |
| ids.openalex | https://openalex.org/W4290944058 |
| fwci | 44.90566065 |
| type | article |
| title | Mask and Reason |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | 1130 |
| biblio.first_page | 1120 |
| topics[0].id | https://openalex.org/T10149 |
| topics[0].field.id | https://openalex.org/fields/33 |
| topics[0].field.display_name | Social Sciences |
| topics[0].score | 0.9359999895095825 |
| topics[0].domain.id | https://openalex.org/domains/2 |
| topics[0].domain.display_name | Social Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/3314 |
| topics[0].subfield.display_name | Anthropology |
| topics[0].display_name | Anthropological Studies and Insights |
| topics[1].id | https://openalex.org/T10994 |
| topics[1].field.id | https://openalex.org/fields/33 |
| topics[1].field.display_name | Social Sciences |
| topics[1].score | 0.9301000237464905 |
| topics[1].domain.id | https://openalex.org/domains/2 |
| topics[1].domain.display_name | Social Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/3312 |
| topics[1].subfield.display_name | Sociology and Political Science |
| topics[1].display_name | Terrorism, Counterterrorism, and Political Violence |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.5085662603378296 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.5085662603378296 |
| keywords[0].display_name | Computer science |
| language | en |
| locations[0].id | doi:10.1145/3534678.3539472 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4363608767 |
| locations[0].source.issn | |
| locations[0].source.type | conference |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining |
| locations[0].source.host_organization | |
| locations[0].source.host_organization_name | |
| locations[0].license | |
| locations[0].pdf_url | https://dl.acm.org/doi/pdf/10.1145/3534678.3539472 |
| locations[0].version | publishedVersion |
| locations[0].raw_type | proceedings-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining |
| locations[0].landing_page_url | https://doi.org/10.1145/3534678.3539472 |
| locations[1].id | pmh:oai:arXiv.org:2208.07638 |
| 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/2208.07638 |
| locations[1].version | submittedVersion |
| locations[1].raw_type | text |
| 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/2208.07638 |
| indexed_in | arxiv, crossref |
| authorships[0].author.id | https://openalex.org/A5100441094 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-9226-4569 |
| authorships[0].author.display_name | Xiao Liu |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I99065089 |
| authorships[0].affiliations[0].raw_affiliation_string | Tsinghua University, Beijing, China |
| authorships[0].institutions[0].id | https://openalex.org/I99065089 |
| authorships[0].institutions[0].ror | https://ror.org/03cve4549 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I99065089 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | Tsinghua University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Xiao Liu |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Tsinghua University, Beijing, China |
| authorships[1].author.id | https://openalex.org/A5052346042 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-3098-8059 |
| authorships[1].author.display_name | Shiyu Zhao |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I99065089 |
| authorships[1].affiliations[0].raw_affiliation_string | Tsinghua University, Beijing, China |
| authorships[1].institutions[0].id | https://openalex.org/I99065089 |
| authorships[1].institutions[0].ror | https://ror.org/03cve4549 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I99065089 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | Tsinghua University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Shiyu Zhao |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Tsinghua University, Beijing, China |
| authorships[2].author.id | https://openalex.org/A5103567928 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Kai Su |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I99065089 |
| authorships[2].affiliations[0].raw_affiliation_string | Tsinghua University, Beijing, China |
| authorships[2].institutions[0].id | https://openalex.org/I99065089 |
| authorships[2].institutions[0].ror | https://ror.org/03cve4549 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I99065089 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | Tsinghua University |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Kai Su |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Tsinghua University, Beijing, China |
| authorships[3].author.id | https://openalex.org/A5035985651 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-5682-2810 |
| authorships[3].author.display_name | Yukuo Cen |
| authorships[3].countries | CN |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I99065089 |
| authorships[3].affiliations[0].raw_affiliation_string | Tsinghua University, Beijing, China |
| authorships[3].institutions[0].id | https://openalex.org/I99065089 |
| authorships[3].institutions[0].ror | https://ror.org/03cve4549 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I99065089 |
| authorships[3].institutions[0].country_code | CN |
| authorships[3].institutions[0].display_name | Tsinghua University |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Yukuo Cen |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Tsinghua University, Beijing, China |
| authorships[4].author.id | https://openalex.org/A5083333630 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-9514-0708 |
| authorships[4].author.display_name | Jiezhong Qiu |
| authorships[4].countries | CN |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I99065089 |
| authorships[4].affiliations[0].raw_affiliation_string | Tsinghua University, Beijing, China |
| authorships[4].institutions[0].id | https://openalex.org/I99065089 |
| authorships[4].institutions[0].ror | https://ror.org/03cve4549 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I99065089 |
| authorships[4].institutions[0].country_code | CN |
| authorships[4].institutions[0].display_name | Tsinghua University |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Jiezhong Qiu |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | Tsinghua University, Beijing, China |
| authorships[5].author.id | https://openalex.org/A5100717443 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-3239-4804 |
| authorships[5].author.display_name | Mengdi Zhang |
| authorships[5].affiliations[0].raw_affiliation_string | Meituan-Dianping Group, Beijing, China |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Mengdi Zhang |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | Meituan-Dianping Group, Beijing, China |
| authorships[6].author.id | https://openalex.org/A5036683934 |
| authorships[6].author.orcid | https://orcid.org/0000-0003-4310-9965 |
| authorships[6].author.display_name | Wei Biao Wu |
| authorships[6].affiliations[0].raw_affiliation_string | Meituan-Dianping Group, Beijing, China |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Wei Wu |
| authorships[6].is_corresponding | False |
| authorships[6].raw_affiliation_strings | Meituan-Dianping Group, Beijing, China |
| authorships[7].author.id | https://openalex.org/A5052284218 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-6092-2002 |
| authorships[7].author.display_name | Yuxiao Dong |
| authorships[7].countries | CN |
| authorships[7].affiliations[0].institution_ids | https://openalex.org/I99065089 |
| authorships[7].affiliations[0].raw_affiliation_string | Tsinghua University, Beijing, China |
| authorships[7].institutions[0].id | https://openalex.org/I99065089 |
| authorships[7].institutions[0].ror | https://ror.org/03cve4549 |
| authorships[7].institutions[0].type | education |
| authorships[7].institutions[0].lineage | https://openalex.org/I99065089 |
| authorships[7].institutions[0].country_code | CN |
| authorships[7].institutions[0].display_name | Tsinghua University |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Yuxiao Dong |
| authorships[7].is_corresponding | False |
| authorships[7].raw_affiliation_strings | Tsinghua University, Beijing, China |
| authorships[8].author.id | https://openalex.org/A5044791875 |
| authorships[8].author.orcid | https://orcid.org/0000-0003-3487-4593 |
| authorships[8].author.display_name | Jie Tang |
| authorships[8].countries | CN |
| authorships[8].affiliations[0].institution_ids | https://openalex.org/I99065089 |
| authorships[8].affiliations[0].raw_affiliation_string | Tsinghua University, Beijing, China |
| authorships[8].institutions[0].id | https://openalex.org/I99065089 |
| authorships[8].institutions[0].ror | https://ror.org/03cve4549 |
| authorships[8].institutions[0].type | education |
| authorships[8].institutions[0].lineage | https://openalex.org/I99065089 |
| authorships[8].institutions[0].country_code | CN |
| authorships[8].institutions[0].display_name | Tsinghua University |
| authorships[8].author_position | last |
| authorships[8].raw_author_name | Jie Tang |
| authorships[8].is_corresponding | False |
| authorships[8].raw_affiliation_strings | Tsinghua University, Beijing, China |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://dl.acm.org/doi/pdf/10.1145/3534678.3539472 |
| open_access.oa_status | bronze |
| open_access.any_repository_has_fulltext | False |
| created_date | 2022-08-13T00:00:00 |
| display_name | Mask and Reason |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10149 |
| primary_topic.field.id | https://openalex.org/fields/33 |
| primary_topic.field.display_name | Social Sciences |
| primary_topic.score | 0.9359999895095825 |
| primary_topic.domain.id | https://openalex.org/domains/2 |
| primary_topic.domain.display_name | Social Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/3314 |
| primary_topic.subfield.display_name | Anthropology |
| primary_topic.display_name | Anthropological Studies and Insights |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W4391913857, https://openalex.org/W2358668433, https://openalex.org/W4396701345, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W4396696052 |
| cited_by_count | 35 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 7 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 16 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 11 |
| counts_by_year[3].year | 2022 |
| counts_by_year[3].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | doi:10.1145/3534678.3539472 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4363608767 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | conference |
| best_oa_location.source.is_oa | False |
| 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 | Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining |
| best_oa_location.source.host_organization | |
| best_oa_location.source.host_organization_name | |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://dl.acm.org/doi/pdf/10.1145/3534678.3539472 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | proceedings-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 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining |
| best_oa_location.landing_page_url | https://doi.org/10.1145/3534678.3539472 |
| primary_location.id | doi:10.1145/3534678.3539472 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4363608767 |
| primary_location.source.issn | |
| primary_location.source.type | conference |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining |
| primary_location.source.host_organization | |
| primary_location.source.host_organization_name | |
| primary_location.license | |
| primary_location.pdf_url | https://dl.acm.org/doi/pdf/10.1145/3534678.3539472 |
| primary_location.version | publishedVersion |
| primary_location.raw_type | proceedings-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining |
| primary_location.landing_page_url | https://doi.org/10.1145/3534678.3539472 |
| publication_date | 2022-08-12 |
| publication_year | 2022 |
| referenced_works | https://openalex.org/W2094728533, https://openalex.org/W1512387364, https://openalex.org/W2016753842, https://openalex.org/W4205460703, https://openalex.org/W3021975806, https://openalex.org/W3080997787, https://openalex.org/W4234672050, https://openalex.org/W3173749507, https://openalex.org/W3036446966, https://openalex.org/W2981852735, https://openalex.org/W4285172793, https://openalex.org/W1757990252, https://openalex.org/W2963690776, https://openalex.org/W2080133951, https://openalex.org/W2128407051, https://openalex.org/W2962886429, https://openalex.org/W6784694379, https://openalex.org/W2952205826, https://openalex.org/W3211394146, https://openalex.org/W4294371460, https://openalex.org/W3203366473, https://openalex.org/W2995448904, https://openalex.org/W3094587024, https://openalex.org/W4300598253, https://openalex.org/W3124660976, https://openalex.org/W3138895808, https://openalex.org/W4385245566, https://openalex.org/W4288356298, https://openalex.org/W2093397547, https://openalex.org/W4293718192, https://openalex.org/W2896457183, https://openalex.org/W3012871709, https://openalex.org/W4288022804, https://openalex.org/W3209807061, https://openalex.org/W3034772996, https://openalex.org/W2899663614, https://openalex.org/W3095602948, https://openalex.org/W4300885858, https://openalex.org/W4287816895, https://openalex.org/W2908510526, https://openalex.org/W3094275584, https://openalex.org/W2952068915, https://openalex.org/W3037208489, https://openalex.org/W3005977214, https://openalex.org/W2127795553, https://openalex.org/W3040573126, https://openalex.org/W3122902162, https://openalex.org/W2250184916, https://openalex.org/W4288089799, https://openalex.org/W2432356473, https://openalex.org/W2970066309, https://openalex.org/W3005552578, https://openalex.org/W3173151551, https://openalex.org/W87564900, https://openalex.org/W3099152386, https://openalex.org/W3100078588 |
| referenced_works_count | 56 |
| abstract_inverted_index.a | 6, 60, 90 |
| abstract_inverted_index.In | 44 |
| abstract_inverted_index.KG | 61, 109 |
| abstract_inverted_index.We | 58, 79 |
| abstract_inverted_index.as | 85 |
| abstract_inverted_index.by | 15, 74 |
| abstract_inverted_index.is | 71 |
| abstract_inverted_index.on | 29, 100 |
| abstract_inverted_index.to | 65, 67, 94, 131 |
| abstract_inverted_index.we | 47 |
| abstract_inverted_index.and | 19, 40, 88, 97, 112, 117 |
| abstract_inverted_index.can | 22, 122 |
| abstract_inverted_index.for | 9 |
| abstract_inverted_index.the | 26, 82, 128 |
| abstract_inverted_index.two | 101 |
| abstract_inverted_index.via | 126 |
| abstract_inverted_index.(KG) | 2 |
| abstract_inverted_index.KGs, | 69 |
| abstract_inverted_index.KGs. | 12 |
| abstract_inverted_index.been | 5 |
| abstract_inverted_index.both | 108 |
| abstract_inverted_index.deal | 24 |
| abstract_inverted_index.full | 129 |
| abstract_inverted_index.have | 4 |
| abstract_inverted_index.nine | 115 |
| abstract_inverted_index.that | 104 |
| abstract_inverted_index.then | 80 |
| abstract_inverted_index.they | 21 |
| abstract_inverted_index.this | 45 |
| abstract_inverted_index.with | 25, 53, 124 |
| abstract_inverted_index.(MoE) | 76 |
| abstract_inverted_index.Graph | 50 |
| abstract_inverted_index.focus | 28 |
| abstract_inverted_index.given | 133 |
| abstract_inverted_index.graph | 1 |
| abstract_inverted_index.their | 16 |
| abstract_inverted_index.which | 32, 70 |
| abstract_inverted_index.work, | 46 |
| abstract_inverted_index.design | 59 |
| abstract_inverted_index.edges, | 37 |
| abstract_inverted_index.handle | 68 |
| abstract_inverted_index.hardly | 23 |
| abstract_inverted_index.masked | 54, 86 |
| abstract_inverted_index.method | 64 |
| abstract_inverted_index.reason | 123 |
| abstract_inverted_index.rising | 27 |
| abstract_inverted_index.sparse | 77 |
| abstract_inverted_index.tasks. | 120 |
| abstract_inverted_index.triple | 62 |
| abstract_inverted_index.complex | 30 |
| abstract_inverted_index.further | 72 |
| abstract_inverted_index.improve | 95 |
| abstract_inverted_index.imputed | 36 |
| abstract_inverted_index.limited | 14 |
| abstract_inverted_index.logical | 34 |
| abstract_inverted_index.present | 48 |
| abstract_inverted_index.queries | 84 |
| abstract_inverted_index.shallow | 18 |
| abstract_inverted_index.unknown | 41 |
| abstract_inverted_index.However, | 13 |
| abstract_inverted_index.advanced | 113 |
| abstract_inverted_index.approach | 8 |
| abstract_inverted_index.comprise | 33 |
| abstract_inverted_index.multiple | 38 |
| abstract_inverted_index.strategy | 93 |
| abstract_inverted_index.Knowledge | 0 |
| abstract_inverted_index.baselines | 111 |
| abstract_inverted_index.entities. | 43 |
| abstract_inverted_index.formulate | 81 |
| abstract_inverted_index.in-domain | 116 |
| abstract_inverted_index.interpret | 132 |
| abstract_inverted_index.introduce | 89 |
| abstract_inverted_index.providing | 127 |
| abstract_inverted_index.reasoning | 119 |
| abstract_inverted_index.two-stage | 91 |
| abstract_inverted_index.answers.\n | 134 |
| abstract_inverted_index.benchmarks | 102 |
| abstract_inverted_index.embeddings | 3 |
| abstract_inverted_index.incomplete | 11 |
| abstract_inverted_index.inherently | 17 |
| abstract_inverted_index.mainstream | 7 |
| abstract_inverted_index.operators, | 35 |
| abstract_inverted_index.outperform | 107 |
| abstract_inverted_index.prediction | 87 |
| abstract_inverted_index.Transformer | 51 |
| abstract_inverted_index.activation. | 78 |
| abstract_inverted_index.demonstrate | 103 |
| abstract_inverted_index.experiments | 99 |
| abstract_inverted_index.strategies. | 57 |
| abstract_inverted_index.encoders\non | 114 |
| abstract_inverted_index.intermediate | 42 |
| abstract_inverted_index.pre-training | 55 |
| abstract_inverted_index.strengthened | 73 |
| abstract_inverted_index.kgTransformer | 105 |
| abstract_inverted_index.out-of-domain | 118 |
| abstract_inverted_index.explainability | 125 |
| abstract_inverted_index.the\nKnowledge | 49 |
| abstract_inverted_index.transformation | 63 |
| abstract_inverted_index.(kgTransformer) | 52 |
| abstract_inverted_index.embedding-based | 110 |
| abstract_inverted_index.reasoning\nover | 10 |
| abstract_inverted_index.transferability | 96 |
| abstract_inverted_index.and\nfine-tuning | 56 |
| abstract_inverted_index.complex\nlogical | 83 |
| abstract_inverted_index.reasoning\npaths | 130 |
| abstract_inverted_index.can\nconsistently | 106 |
| abstract_inverted_index.logical\nqueries, | 31 |
| abstract_inverted_index.source\nentities, | 39 |
| abstract_inverted_index.enable\nTransformer | 66 |
| abstract_inverted_index.masked\npre-training | 92 |
| abstract_inverted_index.static\narchitectures, | 20 |
| abstract_inverted_index.the\nMixture-of-Experts | 75 |
| abstract_inverted_index.Additionally,\nkgTransformer | 121 |
| abstract_inverted_index.generalizability.\nExtensive | 98 |
| cited_by_percentile_year.max | 100 |
| cited_by_percentile_year.min | 89 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 9 |
| citation_normalized_percentile.value | 1.0 |
| citation_normalized_percentile.is_in_top_1_percent | True |
| citation_normalized_percentile.is_in_top_10_percent | True |