Practical token pruning for foundation models in few-shot conversational virtual assistant systems Article Swipe
Haode Qi
,
Cheng Qian
,
Jian Ni
,
Pratyush Singh
,
Reza Fazeli
,
Gengyu Wang
,
Zhenqiu Shu
,
Eric Wayne
,
Juergen Bross
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2408.11799
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2408.11799
In an enterprise Virtual Assistant (VA) system, intent classification is the crucial component that determines how a user input is handled based on what the user wants. The VA system is expected to be a cost-efficient SaaS service with low training and inference time while achieving high accuracy even with a small number of training samples. We pretrain a transformer-based sentence embedding model with a contrastive learning objective and leverage the embedding of the model as features when training intent classification models. Our approach achieves the state-of-the-art results for few-shot scenarios and performs better than other commercial solutions on popular intent classification benchmarks. However, generating features via a transformer-based model increases the inference time, especially for longer user inputs, due to the quadratic runtime of the transformer's attention mechanism. On top of model distillation, we introduce a practical multi-task adaptation approach that configures dynamic token pruning without the need for task-specific training for intent classification. We demonstrate that this approach improves the inference speed of popular sentence transformer models without affecting model performance.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2408.11799
- https://arxiv.org/pdf/2408.11799
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4405419027
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4405419027Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2408.11799Digital Object Identifier
- Title
-
Practical token pruning for foundation models in few-shot conversational virtual assistant systemsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-08-21Full publication date if available
- Authors
-
Haode Qi, Cheng Qian, Jian Ni, Pratyush Singh, Reza Fazeli, Gengyu Wang, Zhenqiu Shu, Eric Wayne, Juergen BrossList of authors in order
- Landing page
-
https://arxiv.org/abs/2408.11799Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2408.11799Direct 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/2408.11799Direct OA link when available
- Concepts
-
Security token, Foundation (evidence), Pruning, Shot (pellet), Computer science, One shot, Artificial intelligence, Human–computer interaction, Computer security, Engineering, Geography, Organic chemistry, Archaeology, Mechanical engineering, Chemistry, Agronomy, BiologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4405419027 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2408.11799 |
| ids.doi | https://doi.org/10.48550/arxiv.2408.11799 |
| ids.openalex | https://openalex.org/W4405419027 |
| fwci | |
| type | preprint |
| title | Practical token pruning for foundation models in few-shot conversational virtual assistant systems |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12031 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9864000082015991 |
| 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 | Speech and dialogue systems |
| topics[1].id | https://openalex.org/T10456 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9689000248908997 |
| 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 | Multi-Agent Systems and Negotiation |
| topics[2].id | https://openalex.org/T10181 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9666000008583069 |
| 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 | 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 | 0.8249666690826416 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1335365 |
| concepts[0].display_name | Security token |
| concepts[1].id | https://openalex.org/C2780966255 |
| concepts[1].level | 2 |
| concepts[1].score | 0.743408739566803 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q5474306 |
| concepts[1].display_name | Foundation (evidence) |
| concepts[2].id | https://openalex.org/C108010975 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6900599598884583 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q500094 |
| concepts[2].display_name | Pruning |
| concepts[3].id | https://openalex.org/C2778344882 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6761057376861572 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q278938 |
| concepts[3].display_name | Shot (pellet) |
| concepts[4].id | https://openalex.org/C41008148 |
| concepts[4].level | 0 |
| concepts[4].score | 0.619337260723114 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[4].display_name | Computer science |
| concepts[5].id | https://openalex.org/C2992734406 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5082723498344421 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q413267 |
| concepts[5].display_name | One shot |
| concepts[6].id | https://openalex.org/C154945302 |
| concepts[6].level | 1 |
| concepts[6].score | 0.40008583664894104 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[6].display_name | Artificial intelligence |
| concepts[7].id | https://openalex.org/C107457646 |
| concepts[7].level | 1 |
| concepts[7].score | 0.35694625973701477 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q207434 |
| concepts[7].display_name | Human–computer interaction |
| concepts[8].id | https://openalex.org/C38652104 |
| concepts[8].level | 1 |
| concepts[8].score | 0.30192816257476807 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[8].display_name | Computer security |
| concepts[9].id | https://openalex.org/C127413603 |
| concepts[9].level | 0 |
| concepts[9].score | 0.23420238494873047 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[9].display_name | Engineering |
| concepts[10].id | https://openalex.org/C205649164 |
| concepts[10].level | 0 |
| concepts[10].score | 0.10544589161872864 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q1071 |
| concepts[10].display_name | Geography |
| concepts[11].id | https://openalex.org/C178790620 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q11351 |
| concepts[11].display_name | Organic chemistry |
| concepts[12].id | https://openalex.org/C166957645 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q23498 |
| concepts[12].display_name | Archaeology |
| concepts[13].id | https://openalex.org/C78519656 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q101333 |
| concepts[13].display_name | Mechanical engineering |
| concepts[14].id | https://openalex.org/C185592680 |
| concepts[14].level | 0 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[14].display_name | Chemistry |
| concepts[15].id | https://openalex.org/C6557445 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q173113 |
| concepts[15].display_name | Agronomy |
| concepts[16].id | https://openalex.org/C86803240 |
| concepts[16].level | 0 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[16].display_name | Biology |
| keywords[0].id | https://openalex.org/keywords/security-token |
| keywords[0].score | 0.8249666690826416 |
| keywords[0].display_name | Security token |
| keywords[1].id | https://openalex.org/keywords/foundation |
| keywords[1].score | 0.743408739566803 |
| keywords[1].display_name | Foundation (evidence) |
| keywords[2].id | https://openalex.org/keywords/pruning |
| keywords[2].score | 0.6900599598884583 |
| keywords[2].display_name | Pruning |
| keywords[3].id | https://openalex.org/keywords/shot |
| keywords[3].score | 0.6761057376861572 |
| keywords[3].display_name | Shot (pellet) |
| keywords[4].id | https://openalex.org/keywords/computer-science |
| keywords[4].score | 0.619337260723114 |
| keywords[4].display_name | Computer science |
| keywords[5].id | https://openalex.org/keywords/one-shot |
| keywords[5].score | 0.5082723498344421 |
| keywords[5].display_name | One shot |
| keywords[6].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[6].score | 0.40008583664894104 |
| keywords[6].display_name | Artificial intelligence |
| keywords[7].id | https://openalex.org/keywords/human–computer-interaction |
| keywords[7].score | 0.35694625973701477 |
| keywords[7].display_name | Human–computer interaction |
| keywords[8].id | https://openalex.org/keywords/computer-security |
| keywords[8].score | 0.30192816257476807 |
| keywords[8].display_name | Computer security |
| keywords[9].id | https://openalex.org/keywords/engineering |
| keywords[9].score | 0.23420238494873047 |
| keywords[9].display_name | Engineering |
| keywords[10].id | https://openalex.org/keywords/geography |
| keywords[10].score | 0.10544589161872864 |
| keywords[10].display_name | Geography |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2408.11799 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2408.11799 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2408.11799 |
| locations[1].id | doi:10.48550/arxiv.2408.11799 |
| 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 | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| 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.2408.11799 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5008247625 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Haode Qi |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Qi, Haode |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100966459 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-9913-820X |
| authorships[1].author.display_name | Cheng Qian |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Qian, Cheng |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5102724821 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-9307-4783 |
| authorships[2].author.display_name | Jian Ni |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Ni, Jian |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5037122155 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-1818-9724 |
| authorships[3].author.display_name | Pratyush Singh |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Singh, Pratyush |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5069042586 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-0322-5235 |
| authorships[4].author.display_name | Reza Fazeli |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Fazeli, Reza |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5091186428 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Gengyu Wang |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Wang, Gengyu |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5052478171 |
| authorships[6].author.orcid | https://orcid.org/0009-0007-7972-1300 |
| authorships[6].author.display_name | Zhenqiu Shu |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Shu, Zhongzheng |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5099137290 |
| authorships[7].author.orcid | |
| authorships[7].author.display_name | Eric Wayne |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Wayne, Eric |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5012628002 |
| authorships[8].author.orcid | |
| authorships[8].author.display_name | Juergen Bross |
| authorships[8].author_position | last |
| authorships[8].raw_author_name | Bross, Juergen |
| authorships[8].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2408.11799 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Practical token pruning for foundation models in few-shot conversational virtual assistant systems |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T12031 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9864000082015991 |
| 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 | Speech and dialogue systems |
| related_works | https://openalex.org/W2497720472, https://openalex.org/W4292659306, https://openalex.org/W3044321615, https://openalex.org/W2806221744, https://openalex.org/W2326937258, https://openalex.org/W394267150, https://openalex.org/W2773965352, https://openalex.org/W4294892107, https://openalex.org/W2357748469, https://openalex.org/W2392917037 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2408.11799 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2408.11799 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2408.11799 |
| primary_location.id | pmh:oai:arXiv.org:2408.11799 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2408.11799 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2408.11799 |
| publication_date | 2024-08-21 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 16, 34, 50, 58, 64, 107, 136 |
| abstract_inverted_index.In | 0 |
| abstract_inverted_index.On | 129 |
| abstract_inverted_index.VA | 28 |
| abstract_inverted_index.We | 56, 155 |
| abstract_inverted_index.an | 1 |
| abstract_inverted_index.as | 75 |
| abstract_inverted_index.be | 33 |
| abstract_inverted_index.is | 9, 19, 30 |
| abstract_inverted_index.of | 53, 72, 124, 131, 164 |
| abstract_inverted_index.on | 22, 98 |
| abstract_inverted_index.to | 32, 120 |
| abstract_inverted_index.we | 134 |
| abstract_inverted_index.Our | 82 |
| abstract_inverted_index.The | 27 |
| abstract_inverted_index.and | 41, 68, 91 |
| abstract_inverted_index.due | 119 |
| abstract_inverted_index.for | 88, 115, 149, 152 |
| abstract_inverted_index.how | 15 |
| abstract_inverted_index.low | 39 |
| abstract_inverted_index.the | 10, 24, 70, 73, 85, 111, 121, 125, 147, 161 |
| abstract_inverted_index.top | 130 |
| abstract_inverted_index.via | 106 |
| abstract_inverted_index.(VA) | 5 |
| abstract_inverted_index.SaaS | 36 |
| abstract_inverted_index.even | 48 |
| abstract_inverted_index.high | 46 |
| abstract_inverted_index.need | 148 |
| abstract_inverted_index.than | 94 |
| abstract_inverted_index.that | 13, 141, 157 |
| abstract_inverted_index.this | 158 |
| abstract_inverted_index.time | 43 |
| abstract_inverted_index.user | 17, 25, 117 |
| abstract_inverted_index.what | 23 |
| abstract_inverted_index.when | 77 |
| abstract_inverted_index.with | 38, 49, 63 |
| abstract_inverted_index.based | 21 |
| abstract_inverted_index.input | 18 |
| abstract_inverted_index.model | 62, 74, 109, 132, 171 |
| abstract_inverted_index.other | 95 |
| abstract_inverted_index.small | 51 |
| abstract_inverted_index.speed | 163 |
| abstract_inverted_index.time, | 113 |
| abstract_inverted_index.token | 144 |
| abstract_inverted_index.while | 44 |
| abstract_inverted_index.better | 93 |
| abstract_inverted_index.intent | 7, 79, 100, 153 |
| abstract_inverted_index.longer | 116 |
| abstract_inverted_index.models | 168 |
| abstract_inverted_index.number | 52 |
| abstract_inverted_index.system | 29 |
| abstract_inverted_index.wants. | 26 |
| abstract_inverted_index.Virtual | 3 |
| abstract_inverted_index.crucial | 11 |
| abstract_inverted_index.dynamic | 143 |
| abstract_inverted_index.handled | 20 |
| abstract_inverted_index.inputs, | 118 |
| abstract_inverted_index.models. | 81 |
| abstract_inverted_index.popular | 99, 165 |
| abstract_inverted_index.pruning | 145 |
| abstract_inverted_index.results | 87 |
| abstract_inverted_index.runtime | 123 |
| abstract_inverted_index.service | 37 |
| abstract_inverted_index.system, | 6 |
| abstract_inverted_index.without | 146, 169 |
| abstract_inverted_index.However, | 103 |
| abstract_inverted_index.accuracy | 47 |
| abstract_inverted_index.achieves | 84 |
| abstract_inverted_index.approach | 83, 140, 159 |
| abstract_inverted_index.expected | 31 |
| abstract_inverted_index.features | 76, 105 |
| abstract_inverted_index.few-shot | 89 |
| abstract_inverted_index.improves | 160 |
| abstract_inverted_index.learning | 66 |
| abstract_inverted_index.leverage | 69 |
| abstract_inverted_index.performs | 92 |
| abstract_inverted_index.pretrain | 57 |
| abstract_inverted_index.samples. | 55 |
| abstract_inverted_index.sentence | 60, 166 |
| abstract_inverted_index.training | 40, 54, 78, 151 |
| abstract_inverted_index.Assistant | 4 |
| abstract_inverted_index.achieving | 45 |
| abstract_inverted_index.affecting | 170 |
| abstract_inverted_index.attention | 127 |
| abstract_inverted_index.component | 12 |
| abstract_inverted_index.embedding | 61, 71 |
| abstract_inverted_index.increases | 110 |
| abstract_inverted_index.inference | 42, 112, 162 |
| abstract_inverted_index.introduce | 135 |
| abstract_inverted_index.objective | 67 |
| abstract_inverted_index.practical | 137 |
| abstract_inverted_index.quadratic | 122 |
| abstract_inverted_index.scenarios | 90 |
| abstract_inverted_index.solutions | 97 |
| abstract_inverted_index.adaptation | 139 |
| abstract_inverted_index.commercial | 96 |
| abstract_inverted_index.configures | 142 |
| abstract_inverted_index.determines | 14 |
| abstract_inverted_index.enterprise | 2 |
| abstract_inverted_index.especially | 114 |
| abstract_inverted_index.generating | 104 |
| abstract_inverted_index.mechanism. | 128 |
| abstract_inverted_index.multi-task | 138 |
| abstract_inverted_index.benchmarks. | 102 |
| abstract_inverted_index.contrastive | 65 |
| abstract_inverted_index.demonstrate | 156 |
| abstract_inverted_index.transformer | 167 |
| abstract_inverted_index.performance. | 172 |
| abstract_inverted_index.distillation, | 133 |
| abstract_inverted_index.task-specific | 150 |
| abstract_inverted_index.transformer's | 126 |
| abstract_inverted_index.classification | 8, 80, 101 |
| abstract_inverted_index.cost-efficient | 35 |
| abstract_inverted_index.classification. | 154 |
| abstract_inverted_index.state-of-the-art | 86 |
| abstract_inverted_index.transformer-based | 59, 108 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 9 |
| citation_normalized_percentile |