GraSAME: Injecting Token-Level Structural Information to Pretrained Language Models via Graph-guided Self-Attention Mechanism Article Swipe
Shuzhou Yuan
,
Michael Färber
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2404.06911
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2404.06911
Pretrained Language Models (PLMs) benefit from external knowledge stored in graph structures for various downstream tasks. However, bridging the modality gap between graph structures and text remains a significant challenge. Traditional methods like linearizing graphs for PLMs lose vital graph connectivity, whereas Graph Neural Networks (GNNs) require cumbersome processes for integration into PLMs. In this work, we propose a novel graph-guided self-attention mechanism, GraSAME. GraSAME seamlessly incorporates token-level structural information into PLMs without necessitating additional alignment or concatenation efforts. As an end-to-end, lightweight multimodal module, GraSAME follows a multi-task learning strategy and effectively bridges the gap between graph and textual modalities, facilitating dynamic interactions between GNNs and PLMs. Our experiments on the graph-to-text generation task demonstrate that GraSAME outperforms baseline models and achieves results comparable to state-of-the-art (SOTA) models on WebNLG datasets. Furthermore, compared to SOTA models, GraSAME eliminates the need for extra pre-training tasks to adjust graph inputs and reduces the number of trainable parameters by over 100 million.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2404.06911
- https://arxiv.org/pdf/2404.06911
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4394736700
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4394736700Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2404.06911Digital Object Identifier
- Title
-
GraSAME: Injecting Token-Level Structural Information to Pretrained Language Models via Graph-guided Self-Attention MechanismWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-04-10Full publication date if available
- Authors
-
Shuzhou Yuan, Michael FärberList of authors in order
- Landing page
-
https://arxiv.org/abs/2404.06911Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2404.06911Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2404.06911Direct OA link when available
- Concepts
-
Security token, Mechanism (biology), Computer science, Graph, Language model, Artificial intelligence, Theoretical computer science, Computer security, Epistemology, PhilosophyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4394736700 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2404.06911 |
| ids.doi | https://doi.org/10.48550/arxiv.2404.06911 |
| ids.openalex | https://openalex.org/W4394736700 |
| fwci | |
| type | preprint |
| title | GraSAME: Injecting Token-Level Structural Information to Pretrained Language Models via Graph-guided Self-Attention Mechanism |
| 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 | 0.9987999796867371 |
| 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 | 0.9973000288009644 |
| 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 |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C48145219 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8157685995101929 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1335365 |
| concepts[0].display_name | Security token |
| concepts[1].id | https://openalex.org/C89611455 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7440187931060791 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q6804646 |
| concepts[1].display_name | Mechanism (biology) |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.6771109104156494 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C132525143 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6038177609443665 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q141488 |
| concepts[3].display_name | Graph |
| concepts[4].id | https://openalex.org/C137293760 |
| concepts[4].level | 2 |
| concepts[4].score | 0.49752095341682434 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q3621696 |
| concepts[4].display_name | Language model |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.43337997794151306 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C80444323 |
| concepts[6].level | 1 |
| concepts[6].score | 0.2954782247543335 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2878974 |
| concepts[6].display_name | Theoretical computer science |
| concepts[7].id | https://openalex.org/C38652104 |
| concepts[7].level | 1 |
| concepts[7].score | 0.12611687183380127 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[7].display_name | Computer security |
| concepts[8].id | https://openalex.org/C111472728 |
| concepts[8].level | 1 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q9471 |
| concepts[8].display_name | Epistemology |
| concepts[9].id | https://openalex.org/C138885662 |
| concepts[9].level | 0 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[9].display_name | Philosophy |
| keywords[0].id | https://openalex.org/keywords/security-token |
| keywords[0].score | 0.8157685995101929 |
| keywords[0].display_name | Security token |
| keywords[1].id | https://openalex.org/keywords/mechanism |
| keywords[1].score | 0.7440187931060791 |
| keywords[1].display_name | Mechanism (biology) |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.6771109104156494 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/graph |
| keywords[3].score | 0.6038177609443665 |
| keywords[3].display_name | Graph |
| keywords[4].id | https://openalex.org/keywords/language-model |
| keywords[4].score | 0.49752095341682434 |
| keywords[4].display_name | Language model |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.43337997794151306 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/theoretical-computer-science |
| keywords[6].score | 0.2954782247543335 |
| keywords[6].display_name | Theoretical computer science |
| keywords[7].id | https://openalex.org/keywords/computer-security |
| keywords[7].score | 0.12611687183380127 |
| keywords[7].display_name | Computer security |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2404.06911 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://arxiv.org/pdf/2404.06911 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2404.06911 |
| locations[1].id | doi:10.48550/arxiv.2404.06911 |
| 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 | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2404.06911 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5008824325 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Shuzhou Yuan |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Yuan, Shuzhou |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5031600582 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-5458-8645 |
| authorships[1].author.display_name | Michael Färber |
| authorships[1].author_position | last |
| authorships[1].raw_author_name | Färber, Michael |
| authorships[1].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2404.06911 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-04-12T00:00:00 |
| display_name | GraSAME: Injecting Token-Level Structural Information to Pretrained Language Models via Graph-guided Self-Attention Mechanism |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| 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 | 0.9987999796867371 |
| 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/W4388335561, https://openalex.org/W2970530566, https://openalex.org/W4288261899, https://openalex.org/W4307309205, https://openalex.org/W2967478618, https://openalex.org/W4385009901, https://openalex.org/W4385572700, https://openalex.org/W2997152889, https://openalex.org/W4387768015, https://openalex.org/W4285141722 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2404.06911 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2404.06911 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2404.06911 |
| primary_location.id | pmh:oai:arXiv.org:2404.06911 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://arxiv.org/pdf/2404.06911 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2404.06911 |
| publication_date | 2024-04-10 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 27, 58, 87 |
| abstract_inverted_index.As | 79 |
| abstract_inverted_index.In | 53 |
| abstract_inverted_index.an | 80 |
| abstract_inverted_index.by | 156 |
| abstract_inverted_index.in | 9 |
| abstract_inverted_index.of | 153 |
| abstract_inverted_index.on | 110, 129 |
| abstract_inverted_index.or | 76 |
| abstract_inverted_index.to | 125, 134, 145 |
| abstract_inverted_index.we | 56 |
| abstract_inverted_index.100 | 158 |
| abstract_inverted_index.Our | 108 |
| abstract_inverted_index.and | 24, 91, 98, 106, 121, 149 |
| abstract_inverted_index.for | 12, 35, 49, 141 |
| abstract_inverted_index.gap | 20, 95 |
| abstract_inverted_index.the | 18, 94, 111, 139, 151 |
| abstract_inverted_index.GNNs | 105 |
| abstract_inverted_index.PLMs | 36, 71 |
| abstract_inverted_index.SOTA | 135 |
| abstract_inverted_index.from | 5 |
| abstract_inverted_index.into | 51, 70 |
| abstract_inverted_index.like | 32 |
| abstract_inverted_index.lose | 37 |
| abstract_inverted_index.need | 140 |
| abstract_inverted_index.over | 157 |
| abstract_inverted_index.task | 114 |
| abstract_inverted_index.text | 25 |
| abstract_inverted_index.that | 116 |
| abstract_inverted_index.this | 54 |
| abstract_inverted_index.Graph | 42 |
| abstract_inverted_index.PLMs. | 52, 107 |
| abstract_inverted_index.extra | 142 |
| abstract_inverted_index.graph | 10, 22, 39, 97, 147 |
| abstract_inverted_index.novel | 59 |
| abstract_inverted_index.tasks | 144 |
| abstract_inverted_index.vital | 38 |
| abstract_inverted_index.work, | 55 |
| abstract_inverted_index.(GNNs) | 45 |
| abstract_inverted_index.(PLMs) | 3 |
| abstract_inverted_index.(SOTA) | 127 |
| abstract_inverted_index.Models | 2 |
| abstract_inverted_index.Neural | 43 |
| abstract_inverted_index.WebNLG | 130 |
| abstract_inverted_index.adjust | 146 |
| abstract_inverted_index.graphs | 34 |
| abstract_inverted_index.inputs | 148 |
| abstract_inverted_index.models | 120, 128 |
| abstract_inverted_index.number | 152 |
| abstract_inverted_index.stored | 8 |
| abstract_inverted_index.tasks. | 15 |
| abstract_inverted_index.GraSAME | 64, 85, 117, 137 |
| abstract_inverted_index.benefit | 4 |
| abstract_inverted_index.between | 21, 96, 104 |
| abstract_inverted_index.bridges | 93 |
| abstract_inverted_index.dynamic | 102 |
| abstract_inverted_index.follows | 86 |
| abstract_inverted_index.methods | 31 |
| abstract_inverted_index.models, | 136 |
| abstract_inverted_index.module, | 84 |
| abstract_inverted_index.propose | 57 |
| abstract_inverted_index.reduces | 150 |
| abstract_inverted_index.remains | 26 |
| abstract_inverted_index.require | 46 |
| abstract_inverted_index.results | 123 |
| abstract_inverted_index.textual | 99 |
| abstract_inverted_index.various | 13 |
| abstract_inverted_index.whereas | 41 |
| abstract_inverted_index.without | 72 |
| abstract_inverted_index.GraSAME. | 63 |
| abstract_inverted_index.However, | 16 |
| abstract_inverted_index.Language | 1 |
| abstract_inverted_index.Networks | 44 |
| abstract_inverted_index.achieves | 122 |
| abstract_inverted_index.baseline | 119 |
| abstract_inverted_index.bridging | 17 |
| abstract_inverted_index.compared | 133 |
| abstract_inverted_index.efforts. | 78 |
| abstract_inverted_index.external | 6 |
| abstract_inverted_index.learning | 89 |
| abstract_inverted_index.million. | 159 |
| abstract_inverted_index.modality | 19 |
| abstract_inverted_index.strategy | 90 |
| abstract_inverted_index.alignment | 75 |
| abstract_inverted_index.datasets. | 131 |
| abstract_inverted_index.knowledge | 7 |
| abstract_inverted_index.processes | 48 |
| abstract_inverted_index.trainable | 154 |
| abstract_inverted_index.Pretrained | 0 |
| abstract_inverted_index.additional | 74 |
| abstract_inverted_index.challenge. | 29 |
| abstract_inverted_index.comparable | 124 |
| abstract_inverted_index.cumbersome | 47 |
| abstract_inverted_index.downstream | 14 |
| abstract_inverted_index.eliminates | 138 |
| abstract_inverted_index.generation | 113 |
| abstract_inverted_index.mechanism, | 62 |
| abstract_inverted_index.multi-task | 88 |
| abstract_inverted_index.multimodal | 83 |
| abstract_inverted_index.parameters | 155 |
| abstract_inverted_index.seamlessly | 65 |
| abstract_inverted_index.structural | 68 |
| abstract_inverted_index.structures | 11, 23 |
| abstract_inverted_index.Traditional | 30 |
| abstract_inverted_index.demonstrate | 115 |
| abstract_inverted_index.effectively | 92 |
| abstract_inverted_index.end-to-end, | 81 |
| abstract_inverted_index.experiments | 109 |
| abstract_inverted_index.information | 69 |
| abstract_inverted_index.integration | 50 |
| abstract_inverted_index.lightweight | 82 |
| abstract_inverted_index.linearizing | 33 |
| abstract_inverted_index.modalities, | 100 |
| abstract_inverted_index.outperforms | 118 |
| abstract_inverted_index.significant | 28 |
| abstract_inverted_index.token-level | 67 |
| abstract_inverted_index.Furthermore, | 132 |
| abstract_inverted_index.facilitating | 101 |
| abstract_inverted_index.graph-guided | 60 |
| abstract_inverted_index.incorporates | 66 |
| abstract_inverted_index.interactions | 103 |
| abstract_inverted_index.pre-training | 143 |
| abstract_inverted_index.concatenation | 77 |
| abstract_inverted_index.connectivity, | 40 |
| abstract_inverted_index.graph-to-text | 112 |
| abstract_inverted_index.necessitating | 73 |
| abstract_inverted_index.self-attention | 61 |
| abstract_inverted_index.state-of-the-art | 126 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 2 |
| citation_normalized_percentile |