Fast Vocabulary Projection Method via Clustering for Multilingual Machine Translation on GPU Article Swipe
Hossam Amer
,
Young Jin Kim
,
Mohamed Afify
,
Hitokazu Matsushita
,
Hany Hassan Awadallah
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2208.06874
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2208.06874
Multilingual Neural Machine Translation has been showing great success using transformer models. Deploying these models is challenging because they usually require large vocabulary (vocab) sizes for various languages. This limits the speed of predicting the output tokens in the last vocab projection layer. To alleviate these challenges, this paper proposes a fast vocabulary projection method via clustering which can be used for multilingual transformers on GPUs. First, we offline split the vocab search space into disjoint clusters given the hidden context vector of the decoder output, which results in much smaller vocab columns for vocab projection. Second, at inference time, the proposed method predicts the clusters and candidate active tokens for hidden context vectors at the vocab projection. This paper also includes analysis of different ways of building these clusters in multilingual settings. Our results show end-to-end speed gains in float16 GPU inference up to 25% while maintaining the BLEU score and slightly increasing memory cost. The proposed method speeds up the vocab projection step itself by up to 2.6x. We also conduct an extensive human evaluation to verify the proposed method preserves the quality of the translations from the original model.
Related Topics
Concepts
Computer science
Machine translation
Inference
Cluster analysis
Projection (relational algebra)
Artificial intelligence
Transformer
Vocabulary
Disjoint sets
Context (archaeology)
Translation (biology)
Algorithm
Mathematics
Combinatorics
Philosophy
Biology
Paleontology
Linguistics
Voltage
Chemistry
Biochemistry
Messenger RNA
Gene
Quantum mechanics
Physics
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2208.06874
- https://arxiv.org/pdf/2208.06874
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4292102102
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4292102102Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2208.06874Digital Object Identifier
- Title
-
Fast Vocabulary Projection Method via Clustering for Multilingual Machine Translation on GPUWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-08-14Full publication date if available
- Authors
-
Hossam Amer, Young Jin Kim, Mohamed Afify, Hitokazu Matsushita, Hany Hassan AwadallahList of authors in order
- Landing page
-
https://arxiv.org/abs/2208.06874Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2208.06874Direct 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/2208.06874Direct OA link when available
- Concepts
-
Computer science, Machine translation, Inference, Cluster analysis, Projection (relational algebra), Artificial intelligence, Transformer, Vocabulary, Disjoint sets, Context (archaeology), Translation (biology), Algorithm, Mathematics, Combinatorics, Philosophy, Biology, Paleontology, Linguistics, Voltage, Chemistry, Biochemistry, Messenger RNA, Gene, Quantum mechanics, PhysicsTop 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/W4292102102 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2208.06874 |
| ids.doi | https://doi.org/10.48550/arxiv.2208.06874 |
| ids.openalex | https://openalex.org/W4292102102 |
| fwci | |
| type | preprint |
| title | Fast Vocabulary Projection Method via Clustering for Multilingual Machine Translation on GPU |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10181 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9993000030517578 |
| 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 | Natural Language Processing Techniques |
| topics[1].id | https://openalex.org/T10028 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9958000183105469 |
| 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 | Topic Modeling |
| topics[2].id | https://openalex.org/T11714 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9905999898910522 |
| 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 | Multimodal Machine Learning Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8460642099380493 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C203005215 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6991804242134094 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q79798 |
| concepts[1].display_name | Machine translation |
| concepts[2].id | https://openalex.org/C2776214188 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6712039709091187 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q408386 |
| concepts[2].display_name | Inference |
| concepts[3].id | https://openalex.org/C73555534 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6421384215354919 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q622825 |
| concepts[3].display_name | Cluster analysis |
| concepts[4].id | https://openalex.org/C57493831 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5906431674957275 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q3134666 |
| concepts[4].display_name | Projection (relational algebra) |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.5346665978431702 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C66322947 |
| concepts[6].level | 3 |
| concepts[6].score | 0.48318496346473694 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11658 |
| concepts[6].display_name | Transformer |
| concepts[7].id | https://openalex.org/C2777601683 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4736410677433014 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q6499736 |
| concepts[7].display_name | Vocabulary |
| concepts[8].id | https://openalex.org/C45340560 |
| concepts[8].level | 2 |
| concepts[8].score | 0.46519529819488525 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q215382 |
| concepts[8].display_name | Disjoint sets |
| concepts[9].id | https://openalex.org/C2779343474 |
| concepts[9].level | 2 |
| concepts[9].score | 0.4461379051208496 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q3109175 |
| concepts[9].display_name | Context (archaeology) |
| concepts[10].id | https://openalex.org/C149364088 |
| concepts[10].level | 4 |
| concepts[10].score | 0.413730651140213 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q185917 |
| concepts[10].display_name | Translation (biology) |
| concepts[11].id | https://openalex.org/C11413529 |
| concepts[11].level | 1 |
| concepts[11].score | 0.2471468150615692 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[11].display_name | Algorithm |
| concepts[12].id | https://openalex.org/C33923547 |
| concepts[12].level | 0 |
| concepts[12].score | 0.07234033942222595 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[12].display_name | Mathematics |
| concepts[13].id | https://openalex.org/C114614502 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q76592 |
| concepts[13].display_name | Combinatorics |
| concepts[14].id | https://openalex.org/C138885662 |
| concepts[14].level | 0 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[14].display_name | Philosophy |
| 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 |
| concepts[16].id | https://openalex.org/C151730666 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q7205 |
| concepts[16].display_name | Paleontology |
| concepts[17].id | https://openalex.org/C41895202 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[17].display_name | Linguistics |
| concepts[18].id | https://openalex.org/C165801399 |
| concepts[18].level | 2 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q25428 |
| concepts[18].display_name | Voltage |
| concepts[19].id | https://openalex.org/C185592680 |
| concepts[19].level | 0 |
| concepts[19].score | 0.0 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[19].display_name | Chemistry |
| concepts[20].id | https://openalex.org/C55493867 |
| concepts[20].level | 1 |
| concepts[20].score | 0.0 |
| concepts[20].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[20].display_name | Biochemistry |
| concepts[21].id | https://openalex.org/C105580179 |
| concepts[21].level | 3 |
| concepts[21].score | 0.0 |
| concepts[21].wikidata | https://www.wikidata.org/wiki/Q188928 |
| concepts[21].display_name | Messenger RNA |
| concepts[22].id | https://openalex.org/C104317684 |
| concepts[22].level | 2 |
| concepts[22].score | 0.0 |
| concepts[22].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[22].display_name | Gene |
| concepts[23].id | https://openalex.org/C62520636 |
| concepts[23].level | 1 |
| concepts[23].score | 0.0 |
| concepts[23].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[23].display_name | Quantum mechanics |
| concepts[24].id | https://openalex.org/C121332964 |
| concepts[24].level | 0 |
| concepts[24].score | 0.0 |
| concepts[24].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[24].display_name | Physics |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8460642099380493 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/machine-translation |
| keywords[1].score | 0.6991804242134094 |
| keywords[1].display_name | Machine translation |
| keywords[2].id | https://openalex.org/keywords/inference |
| keywords[2].score | 0.6712039709091187 |
| keywords[2].display_name | Inference |
| keywords[3].id | https://openalex.org/keywords/cluster-analysis |
| keywords[3].score | 0.6421384215354919 |
| keywords[3].display_name | Cluster analysis |
| keywords[4].id | https://openalex.org/keywords/projection |
| keywords[4].score | 0.5906431674957275 |
| keywords[4].display_name | Projection (relational algebra) |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.5346665978431702 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/transformer |
| keywords[6].score | 0.48318496346473694 |
| keywords[6].display_name | Transformer |
| keywords[7].id | https://openalex.org/keywords/vocabulary |
| keywords[7].score | 0.4736410677433014 |
| keywords[7].display_name | Vocabulary |
| keywords[8].id | https://openalex.org/keywords/disjoint-sets |
| keywords[8].score | 0.46519529819488525 |
| keywords[8].display_name | Disjoint sets |
| keywords[9].id | https://openalex.org/keywords/context |
| keywords[9].score | 0.4461379051208496 |
| keywords[9].display_name | Context (archaeology) |
| keywords[10].id | https://openalex.org/keywords/translation |
| keywords[10].score | 0.413730651140213 |
| keywords[10].display_name | Translation (biology) |
| keywords[11].id | https://openalex.org/keywords/algorithm |
| keywords[11].score | 0.2471468150615692 |
| keywords[11].display_name | Algorithm |
| keywords[12].id | https://openalex.org/keywords/mathematics |
| keywords[12].score | 0.07234033942222595 |
| keywords[12].display_name | Mathematics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2208.06874 |
| 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/2208.06874 |
| 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/2208.06874 |
| locations[1].id | doi:10.48550/arxiv.2208.06874 |
| 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.2208.06874 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5022851730 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-1136-227X |
| authorships[0].author.display_name | Hossam Amer |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Amer, Hossam |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100387389 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-2976-3047 |
| authorships[1].author.display_name | Young Jin Kim |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Kim, Young Jin |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5021938376 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-4445-9767 |
| authorships[2].author.display_name | Mohamed Afify |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Afify, Mohamed |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5031892133 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Hitokazu Matsushita |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Matsushita, Hitokazu |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5068313174 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Hany Hassan Awadallah |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Awadallah, Hany Hassan |
| authorships[4].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/2208.06874 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Fast Vocabulary Projection Method via Clustering for Multilingual Machine Translation on GPU |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10181 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9993000030517578 |
| 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 | Natural Language Processing Techniques |
| related_works | https://openalex.org/W3176018525, https://openalex.org/W2903533908, https://openalex.org/W2903810591, https://openalex.org/W3026554633, https://openalex.org/W2888520903, https://openalex.org/W2890256614, https://openalex.org/W2949454572, https://openalex.org/W3066373881, https://openalex.org/W2970247882, https://openalex.org/W4389523797 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2208.06874 |
| 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/2208.06874 |
| 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/2208.06874 |
| primary_location.id | pmh:oai:arXiv.org:2208.06874 |
| 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/2208.06874 |
| 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/2208.06874 |
| publication_date | 2022-08-14 |
| publication_year | 2022 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 50 |
| abstract_inverted_index.To | 43 |
| abstract_inverted_index.We | 170 |
| abstract_inverted_index.an | 173 |
| abstract_inverted_index.at | 97, 114 |
| abstract_inverted_index.be | 59 |
| abstract_inverted_index.by | 166 |
| abstract_inverted_index.in | 37, 88, 130, 139 |
| abstract_inverted_index.is | 15 |
| abstract_inverted_index.of | 32, 82, 123, 126, 185 |
| abstract_inverted_index.on | 64 |
| abstract_inverted_index.to | 144, 168, 177 |
| abstract_inverted_index.up | 143, 160, 167 |
| abstract_inverted_index.we | 67 |
| abstract_inverted_index.25% | 145 |
| abstract_inverted_index.GPU | 141 |
| abstract_inverted_index.Our | 133 |
| abstract_inverted_index.The | 156 |
| abstract_inverted_index.and | 106, 151 |
| abstract_inverted_index.can | 58 |
| abstract_inverted_index.for | 25, 61, 93, 110 |
| abstract_inverted_index.has | 4 |
| abstract_inverted_index.the | 30, 34, 38, 70, 78, 83, 100, 104, 115, 148, 161, 179, 183, 186, 189 |
| abstract_inverted_index.via | 55 |
| abstract_inverted_index.BLEU | 149 |
| abstract_inverted_index.This | 28, 118 |
| abstract_inverted_index.also | 120, 171 |
| abstract_inverted_index.been | 5 |
| abstract_inverted_index.fast | 51 |
| abstract_inverted_index.from | 188 |
| abstract_inverted_index.into | 74 |
| abstract_inverted_index.last | 39 |
| abstract_inverted_index.much | 89 |
| abstract_inverted_index.show | 135 |
| abstract_inverted_index.step | 164 |
| abstract_inverted_index.they | 18 |
| abstract_inverted_index.this | 47 |
| abstract_inverted_index.used | 60 |
| abstract_inverted_index.ways | 125 |
| abstract_inverted_index.2.6x. | 169 |
| abstract_inverted_index.GPUs. | 65 |
| abstract_inverted_index.cost. | 155 |
| abstract_inverted_index.gains | 138 |
| abstract_inverted_index.given | 77 |
| abstract_inverted_index.great | 7 |
| abstract_inverted_index.human | 175 |
| abstract_inverted_index.large | 21 |
| abstract_inverted_index.paper | 48, 119 |
| abstract_inverted_index.score | 150 |
| abstract_inverted_index.sizes | 24 |
| abstract_inverted_index.space | 73 |
| abstract_inverted_index.speed | 31, 137 |
| abstract_inverted_index.split | 69 |
| abstract_inverted_index.these | 13, 45, 128 |
| abstract_inverted_index.time, | 99 |
| abstract_inverted_index.using | 9 |
| abstract_inverted_index.vocab | 40, 71, 91, 94, 116, 162 |
| abstract_inverted_index.which | 57, 86 |
| abstract_inverted_index.while | 146 |
| abstract_inverted_index.First, | 66 |
| abstract_inverted_index.Neural | 1 |
| abstract_inverted_index.active | 108 |
| abstract_inverted_index.hidden | 79, 111 |
| abstract_inverted_index.itself | 165 |
| abstract_inverted_index.layer. | 42 |
| abstract_inverted_index.limits | 29 |
| abstract_inverted_index.memory | 154 |
| abstract_inverted_index.method | 54, 102, 158, 181 |
| abstract_inverted_index.model. | 191 |
| abstract_inverted_index.models | 14 |
| abstract_inverted_index.output | 35 |
| abstract_inverted_index.search | 72 |
| abstract_inverted_index.speeds | 159 |
| abstract_inverted_index.tokens | 36, 109 |
| abstract_inverted_index.vector | 81 |
| abstract_inverted_index.verify | 178 |
| abstract_inverted_index.(vocab) | 23 |
| abstract_inverted_index.Machine | 2 |
| abstract_inverted_index.Second, | 96 |
| abstract_inverted_index.because | 17 |
| abstract_inverted_index.columns | 92 |
| abstract_inverted_index.conduct | 172 |
| abstract_inverted_index.context | 80, 112 |
| abstract_inverted_index.decoder | 84 |
| abstract_inverted_index.float16 | 140 |
| abstract_inverted_index.models. | 11 |
| abstract_inverted_index.offline | 68 |
| abstract_inverted_index.output, | 85 |
| abstract_inverted_index.quality | 184 |
| abstract_inverted_index.require | 20 |
| abstract_inverted_index.results | 87, 134 |
| abstract_inverted_index.showing | 6 |
| abstract_inverted_index.smaller | 90 |
| abstract_inverted_index.success | 8 |
| abstract_inverted_index.usually | 19 |
| abstract_inverted_index.various | 26 |
| abstract_inverted_index.vectors | 113 |
| abstract_inverted_index.analysis | 122 |
| abstract_inverted_index.building | 127 |
| abstract_inverted_index.clusters | 76, 105, 129 |
| abstract_inverted_index.disjoint | 75 |
| abstract_inverted_index.includes | 121 |
| abstract_inverted_index.original | 190 |
| abstract_inverted_index.predicts | 103 |
| abstract_inverted_index.proposed | 101, 157, 180 |
| abstract_inverted_index.proposes | 49 |
| abstract_inverted_index.slightly | 152 |
| abstract_inverted_index.Deploying | 12 |
| abstract_inverted_index.alleviate | 44 |
| abstract_inverted_index.candidate | 107 |
| abstract_inverted_index.different | 124 |
| abstract_inverted_index.extensive | 174 |
| abstract_inverted_index.inference | 98, 142 |
| abstract_inverted_index.preserves | 182 |
| abstract_inverted_index.settings. | 132 |
| abstract_inverted_index.clustering | 56 |
| abstract_inverted_index.end-to-end | 136 |
| abstract_inverted_index.evaluation | 176 |
| abstract_inverted_index.increasing | 153 |
| abstract_inverted_index.languages. | 27 |
| abstract_inverted_index.predicting | 33 |
| abstract_inverted_index.projection | 41, 53, 163 |
| abstract_inverted_index.vocabulary | 22, 52 |
| abstract_inverted_index.Translation | 3 |
| abstract_inverted_index.challenges, | 46 |
| abstract_inverted_index.challenging | 16 |
| abstract_inverted_index.maintaining | 147 |
| abstract_inverted_index.projection. | 95, 117 |
| abstract_inverted_index.transformer | 10 |
| abstract_inverted_index.Multilingual | 0 |
| abstract_inverted_index.multilingual | 62, 131 |
| abstract_inverted_index.transformers | 63 |
| abstract_inverted_index.translations | 187 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.7900000214576721 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile |