Dynamic Transformer for Efficient Machine Translation on Embedded Devices Article Swipe
Hishan Parry
,
Xun Lei
,
Amin Sabet
,
Jia Bi
,
Jonathon Hare
,
Geoff V. Merrett
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.1109/mlcad52597.2021.9531281
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.1109/mlcad52597.2021.9531281
The Transformer architecture is widely used for machine translation tasks. However, its resource-intensive nature makes it challenging to implement on constrained embedded devices, particularly where available hardware resources can vary at run-time. We propose a dynamic machine translation model that scales the Transformer architecture based on the available resources at any particular time. The proposed approach, 'Dynamic-HAT', uses a HAT SuperTransformer as the backbone to search for SubTransformers with different accuracy-latency trade-offs at design time. The optimal SubTransformers are sampled from the SuperTransformer at run-time, depending on latency constraints. The Dynamic-HAT is tested on the Jetson Nano and the approach uses inherited SubTransformers sampled directly from the SuperTransformer with a switching time of <1s. Using inherited SubTransformers results in a BLEU score loss of <1.5% because the SubTransformer configuration is not retrained from scratch after sampling. However, to recover this loss in performance, the dimensions of the design space can be reduced to tailor it to a family of target hardware. The new reduced design space results in a BLEU score increase of approximately 1% for sub-optimal models from the original design space, with a wide range for performance scaling between 0.356s - 1.526s for the GPU and 2.9s - 7.31s for the CPU.
Related Topics
Concepts
Computer science
Transformer
Scratch
Latency (audio)
Machine translation
Design space exploration
Scaling
Architecture
Embedded system
Computer engineering
Real-time computing
Artificial intelligence
Voltage
Operating system
Engineering
Electrical engineering
Mathematics
Telecommunications
Art
Visual arts
Geometry
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.1109/mlcad52597.2021.9531281
- OA Status
- green
- Cited By
- 2
- References
- 25
- Related Works
- 20
- OpenAlex ID
- https://openalex.org/W3185554909
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3185554909Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1109/mlcad52597.2021.9531281Digital Object Identifier
- Title
-
Dynamic Transformer for Efficient Machine Translation on Embedded DevicesWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-08-30Full publication date if available
- Authors
-
Hishan Parry, Xun Lei, Amin Sabet, Jia Bi, Jonathon Hare, Geoff V. MerrettList of authors in order
- Landing page
-
https://doi.org/10.1109/mlcad52597.2021.9531281Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2107.08199Direct OA link when available
- Concepts
-
Computer science, Transformer, Scratch, Latency (audio), Machine translation, Design space exploration, Scaling, Architecture, Embedded system, Computer engineering, Real-time computing, Artificial intelligence, Voltage, Operating system, Engineering, Electrical engineering, Mathematics, Telecommunications, Art, Visual arts, GeometryTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
2Total citation count in OpenAlex
- Citations by year (recent)
-
2023: 2Per-year citation counts (last 5 years)
- References (count)
-
25Number of works referenced by this work
- Related works (count)
-
20Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3185554909 |
|---|---|
| doi | https://doi.org/10.1109/mlcad52597.2021.9531281 |
| ids.doi | https://doi.org/10.1109/mlcad52597.2021.9531281 |
| ids.mag | 3185554909 |
| ids.openalex | https://openalex.org/W3185554909 |
| fwci | 0.28220715 |
| type | preprint |
| title | Dynamic Transformer for Efficient Machine Translation on Embedded Devices |
| awards[0].id | https://openalex.org/G3496335909 |
| awards[0].funder_id | https://openalex.org/F4320334627 |
| awards[0].display_name | |
| awards[0].funder_award_id | EP/S030069/1 |
| awards[0].funder_display_name | Engineering and Physical Sciences Research Council |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | 6 |
| biblio.first_page | 1 |
| 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 | 0.9904999732971191 |
| 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/T12326 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9853000044822693 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1708 |
| topics[1].subfield.display_name | Hardware and Architecture |
| topics[1].display_name | Network Packet Processing and Optimization |
| topics[2].id | https://openalex.org/T10028 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9833999872207642 |
| 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 | Topic Modeling |
| funders[0].id | https://openalex.org/F4320334627 |
| funders[0].ror | https://ror.org/0439y7842 |
| funders[0].display_name | Engineering and Physical Sciences Research Council |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7802629470825195 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C66322947 |
| concepts[1].level | 3 |
| concepts[1].score | 0.6765284538269043 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q11658 |
| concepts[1].display_name | Transformer |
| concepts[2].id | https://openalex.org/C2781235140 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6169134974479675 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q275131 |
| concepts[2].display_name | Scratch |
| concepts[3].id | https://openalex.org/C82876162 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5993115305900574 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q17096504 |
| concepts[3].display_name | Latency (audio) |
| concepts[4].id | https://openalex.org/C203005215 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5427101254463196 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q79798 |
| concepts[4].display_name | Machine translation |
| concepts[5].id | https://openalex.org/C2776221188 |
| concepts[5].level | 2 |
| concepts[5].score | 0.507583737373352 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q21072556 |
| concepts[5].display_name | Design space exploration |
| concepts[6].id | https://openalex.org/C99844830 |
| concepts[6].level | 2 |
| concepts[6].score | 0.47835248708724976 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q102441924 |
| concepts[6].display_name | Scaling |
| concepts[7].id | https://openalex.org/C123657996 |
| concepts[7].level | 2 |
| concepts[7].score | 0.47735074162483215 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q12271 |
| concepts[7].display_name | Architecture |
| concepts[8].id | https://openalex.org/C149635348 |
| concepts[8].level | 1 |
| concepts[8].score | 0.4309234023094177 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q193040 |
| concepts[8].display_name | Embedded system |
| concepts[9].id | https://openalex.org/C113775141 |
| concepts[9].level | 1 |
| concepts[9].score | 0.4050138592720032 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q428691 |
| concepts[9].display_name | Computer engineering |
| concepts[10].id | https://openalex.org/C79403827 |
| concepts[10].level | 1 |
| concepts[10].score | 0.36033451557159424 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q3988 |
| concepts[10].display_name | Real-time computing |
| concepts[11].id | https://openalex.org/C154945302 |
| concepts[11].level | 1 |
| concepts[11].score | 0.29715514183044434 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[11].display_name | Artificial intelligence |
| concepts[12].id | https://openalex.org/C165801399 |
| concepts[12].level | 2 |
| concepts[12].score | 0.1437525451183319 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q25428 |
| concepts[12].display_name | Voltage |
| concepts[13].id | https://openalex.org/C111919701 |
| concepts[13].level | 1 |
| concepts[13].score | 0.10454940795898438 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[13].display_name | Operating system |
| concepts[14].id | https://openalex.org/C127413603 |
| concepts[14].level | 0 |
| concepts[14].score | 0.09100887179374695 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[14].display_name | Engineering |
| concepts[15].id | https://openalex.org/C119599485 |
| concepts[15].level | 1 |
| concepts[15].score | 0.07068651914596558 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q43035 |
| concepts[15].display_name | Electrical engineering |
| concepts[16].id | https://openalex.org/C33923547 |
| concepts[16].level | 0 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[16].display_name | Mathematics |
| concepts[17].id | https://openalex.org/C76155785 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q418 |
| concepts[17].display_name | Telecommunications |
| concepts[18].id | https://openalex.org/C142362112 |
| concepts[18].level | 0 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q735 |
| concepts[18].display_name | Art |
| concepts[19].id | https://openalex.org/C153349607 |
| concepts[19].level | 1 |
| concepts[19].score | 0.0 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q36649 |
| concepts[19].display_name | Visual arts |
| concepts[20].id | https://openalex.org/C2524010 |
| concepts[20].level | 1 |
| concepts[20].score | 0.0 |
| concepts[20].wikidata | https://www.wikidata.org/wiki/Q8087 |
| concepts[20].display_name | Geometry |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7802629470825195 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/transformer |
| keywords[1].score | 0.6765284538269043 |
| keywords[1].display_name | Transformer |
| keywords[2].id | https://openalex.org/keywords/scratch |
| keywords[2].score | 0.6169134974479675 |
| keywords[2].display_name | Scratch |
| keywords[3].id | https://openalex.org/keywords/latency |
| keywords[3].score | 0.5993115305900574 |
| keywords[3].display_name | Latency (audio) |
| keywords[4].id | https://openalex.org/keywords/machine-translation |
| keywords[4].score | 0.5427101254463196 |
| keywords[4].display_name | Machine translation |
| keywords[5].id | https://openalex.org/keywords/design-space-exploration |
| keywords[5].score | 0.507583737373352 |
| keywords[5].display_name | Design space exploration |
| keywords[6].id | https://openalex.org/keywords/scaling |
| keywords[6].score | 0.47835248708724976 |
| keywords[6].display_name | Scaling |
| keywords[7].id | https://openalex.org/keywords/architecture |
| keywords[7].score | 0.47735074162483215 |
| keywords[7].display_name | Architecture |
| keywords[8].id | https://openalex.org/keywords/embedded-system |
| keywords[8].score | 0.4309234023094177 |
| keywords[8].display_name | Embedded system |
| keywords[9].id | https://openalex.org/keywords/computer-engineering |
| keywords[9].score | 0.4050138592720032 |
| keywords[9].display_name | Computer engineering |
| keywords[10].id | https://openalex.org/keywords/real-time-computing |
| keywords[10].score | 0.36033451557159424 |
| keywords[10].display_name | Real-time computing |
| keywords[11].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[11].score | 0.29715514183044434 |
| keywords[11].display_name | Artificial intelligence |
| keywords[12].id | https://openalex.org/keywords/voltage |
| keywords[12].score | 0.1437525451183319 |
| keywords[12].display_name | Voltage |
| keywords[13].id | https://openalex.org/keywords/operating-system |
| keywords[13].score | 0.10454940795898438 |
| keywords[13].display_name | Operating system |
| keywords[14].id | https://openalex.org/keywords/engineering |
| keywords[14].score | 0.09100887179374695 |
| keywords[14].display_name | Engineering |
| keywords[15].id | https://openalex.org/keywords/electrical-engineering |
| keywords[15].score | 0.07068651914596558 |
| keywords[15].display_name | Electrical engineering |
| language | en |
| locations[0].id | doi:10.1109/mlcad52597.2021.9531281 |
| locations[0].is_oa | False |
| locations[0].source | |
| locations[0].license | |
| locations[0].pdf_url | |
| 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 | 2021 ACM/IEEE 3rd Workshop on Machine Learning for CAD (MLCAD) |
| locations[0].landing_page_url | https://doi.org/10.1109/mlcad52597.2021.9531281 |
| locations[1].id | pmh:oai:arXiv.org:2107.08199 |
| 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/2107.08199 |
| locations[1].version | submittedVersion |
| locations[1].raw_type | |
| 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/2107.08199 |
| locations[2].id | pmh:oai:eprints.soton.ac.uk:450548 |
| locations[2].is_oa | True |
| locations[2].source.id | https://openalex.org/S4306401019 |
| locations[2].source.issn | |
| locations[2].source.type | repository |
| locations[2].source.is_oa | False |
| locations[2].source.issn_l | |
| locations[2].source.is_core | False |
| locations[2].source.is_in_doaj | False |
| locations[2].source.display_name | ePrints Soton (University of Southampton) |
| locations[2].source.host_organization | https://openalex.org/I43439940 |
| locations[2].source.host_organization_name | University of Southampton |
| locations[2].source.host_organization_lineage | https://openalex.org/I43439940 |
| locations[2].license | |
| locations[2].pdf_url | https://eprints.soton.ac.uk/450548/1/Dynamic_HAT_MLCAD_2021_Accepted.pdf |
| locations[2].version | submittedVersion |
| locations[2].raw_type | Conference or Workshop Item |
| locations[2].license_id | |
| locations[2].is_accepted | False |
| locations[2].is_published | False |
| locations[2].raw_source_name | |
| locations[2].landing_page_url | |
| locations[3].id | mag:3185554909 |
| locations[3].is_oa | True |
| locations[3].source.id | https://openalex.org/S4306400194 |
| locations[3].source.issn | |
| locations[3].source.type | repository |
| locations[3].source.is_oa | True |
| locations[3].source.issn_l | |
| locations[3].source.is_core | False |
| locations[3].source.is_in_doaj | False |
| locations[3].source.display_name | arXiv (Cornell University) |
| locations[3].source.host_organization | https://openalex.org/I205783295 |
| locations[3].source.host_organization_name | Cornell University |
| locations[3].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[3].license | |
| locations[3].pdf_url | |
| locations[3].version | submittedVersion |
| locations[3].raw_type | |
| locations[3].license_id | |
| locations[3].is_accepted | False |
| locations[3].is_published | False |
| locations[3].raw_source_name | arXiv (Cornell University) |
| locations[3].landing_page_url | https://arxiv.org/pdf/2107.08199 |
| locations[4].id | doi:10.48550/arxiv.2107.08199 |
| locations[4].is_oa | True |
| locations[4].source.id | https://openalex.org/S4306400194 |
| locations[4].source.issn | |
| locations[4].source.type | repository |
| locations[4].source.is_oa | True |
| locations[4].source.issn_l | |
| locations[4].source.is_core | False |
| locations[4].source.is_in_doaj | False |
| locations[4].source.display_name | arXiv (Cornell University) |
| locations[4].source.host_organization | https://openalex.org/I205783295 |
| locations[4].source.host_organization_name | Cornell University |
| locations[4].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[4].license | cc-by |
| locations[4].pdf_url | |
| locations[4].version | |
| locations[4].raw_type | article |
| locations[4].license_id | https://openalex.org/licenses/cc-by |
| locations[4].is_accepted | False |
| locations[4].is_published | |
| locations[4].raw_source_name | |
| locations[4].landing_page_url | https://doi.org/10.48550/arxiv.2107.08199 |
| indexed_in | arxiv, crossref, datacite |
| authorships[0].author.id | https://openalex.org/A5018852650 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Hishan Parry |
| authorships[0].countries | GB |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I43439940 |
| authorships[0].affiliations[0].raw_affiliation_string | University of Southampton, School of Electronics and Computer Science, Southampton, UK |
| authorships[0].institutions[0].id | https://openalex.org/I43439940 |
| authorships[0].institutions[0].ror | https://ror.org/01ryk1543 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I43439940 |
| authorships[0].institutions[0].country_code | GB |
| authorships[0].institutions[0].display_name | University of Southampton |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Hishan Parry |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | University of Southampton, School of Electronics and Computer Science, Southampton, UK |
| authorships[1].author.id | https://openalex.org/A5091490292 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-5118-9294 |
| authorships[1].author.display_name | Xun Lei |
| authorships[1].countries | GB |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I43439940 |
| authorships[1].affiliations[0].raw_affiliation_string | University of Southampton, School of Electronics and Computer Science, Southampton, UK |
| authorships[1].institutions[0].id | https://openalex.org/I43439940 |
| authorships[1].institutions[0].ror | https://ror.org/01ryk1543 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I43439940 |
| authorships[1].institutions[0].country_code | GB |
| authorships[1].institutions[0].display_name | University of Southampton |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Lei Xun |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | University of Southampton, School of Electronics and Computer Science, Southampton, UK |
| authorships[2].author.id | https://openalex.org/A5035478022 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-2625-8344 |
| authorships[2].author.display_name | Amin Sabet |
| authorships[2].countries | GB |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I43439940 |
| authorships[2].affiliations[0].raw_affiliation_string | University of Southampton, School of Electronics and Computer Science, Southampton, UK |
| authorships[2].institutions[0].id | https://openalex.org/I43439940 |
| authorships[2].institutions[0].ror | https://ror.org/01ryk1543 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I43439940 |
| authorships[2].institutions[0].country_code | GB |
| authorships[2].institutions[0].display_name | University of Southampton |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Amin Sabet |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | University of Southampton, School of Electronics and Computer Science, Southampton, UK |
| authorships[3].author.id | https://openalex.org/A5087963759 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-3773-3289 |
| authorships[3].author.display_name | Jia Bi |
| authorships[3].countries | GB |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I43439940 |
| authorships[3].affiliations[0].raw_affiliation_string | University of Southampton, School of Electronics and Computer Science, Southampton, UK |
| authorships[3].institutions[0].id | https://openalex.org/I43439940 |
| authorships[3].institutions[0].ror | https://ror.org/01ryk1543 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I43439940 |
| authorships[3].institutions[0].country_code | GB |
| authorships[3].institutions[0].display_name | University of Southampton |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Jia Bi |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | University of Southampton, School of Electronics and Computer Science, Southampton, UK |
| authorships[4].author.id | https://openalex.org/A5067505586 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-2921-4283 |
| authorships[4].author.display_name | Jonathon Hare |
| authorships[4].countries | GB |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I43439940 |
| authorships[4].affiliations[0].raw_affiliation_string | University of Southampton, School of Electronics and Computer Science, Southampton, UK |
| authorships[4].institutions[0].id | https://openalex.org/I43439940 |
| authorships[4].institutions[0].ror | https://ror.org/01ryk1543 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I43439940 |
| authorships[4].institutions[0].country_code | GB |
| authorships[4].institutions[0].display_name | University of Southampton |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Jonathon Hare |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | University of Southampton, School of Electronics and Computer Science, Southampton, UK |
| authorships[5].author.id | https://openalex.org/A5001556143 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-4980-3894 |
| authorships[5].author.display_name | Geoff V. Merrett |
| authorships[5].countries | GB |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I43439940 |
| authorships[5].affiliations[0].raw_affiliation_string | University of Southampton * |
| authorships[5].institutions[0].id | https://openalex.org/I43439940 |
| authorships[5].institutions[0].ror | https://ror.org/01ryk1543 |
| authorships[5].institutions[0].type | education |
| authorships[5].institutions[0].lineage | https://openalex.org/I43439940 |
| authorships[5].institutions[0].country_code | GB |
| authorships[5].institutions[0].display_name | University of Southampton |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Geoff V. Merrett |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | University of Southampton * |
| 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/2107.08199 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Dynamic Transformer for Efficient Machine Translation on Embedded Devices |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| 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 | 0.9904999732971191 |
| 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/W3203418542, https://openalex.org/W2264258177, https://openalex.org/W2263026745, https://openalex.org/W2315179163, https://openalex.org/W3140491875, https://openalex.org/W2163257571, https://openalex.org/W2991040477, https://openalex.org/W2615432139, https://openalex.org/W2953004927, https://openalex.org/W2533980075, https://openalex.org/W2769798155, https://openalex.org/W2904902613, https://openalex.org/W2183991724, https://openalex.org/W2904283553, https://openalex.org/W2519067463, https://openalex.org/W3083104827, https://openalex.org/W2952859565, https://openalex.org/W2810449665, https://openalex.org/W2604491648, https://openalex.org/W2996960515 |
| cited_by_count | 2 |
| counts_by_year[0].year | 2023 |
| counts_by_year[0].cited_by_count | 2 |
| locations_count | 5 |
| best_oa_location.id | pmh:oai:arXiv.org:2107.08199 |
| 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/2107.08199 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| 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/2107.08199 |
| primary_location.id | doi:10.1109/mlcad52597.2021.9531281 |
| primary_location.is_oa | False |
| primary_location.source | |
| primary_location.license | |
| primary_location.pdf_url | |
| 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 | 2021 ACM/IEEE 3rd Workshop on Machine Learning for CAD (MLCAD) |
| primary_location.landing_page_url | https://doi.org/10.1109/mlcad52597.2021.9531281 |
| publication_date | 2021-08-30 |
| publication_year | 2021 |
| referenced_works | https://openalex.org/W6745148473, https://openalex.org/W2963122961, https://openalex.org/W6778067029, https://openalex.org/W6794716787, https://openalex.org/W6767064347, https://openalex.org/W6898505805, https://openalex.org/W6775706467, https://openalex.org/W3012511001, https://openalex.org/W3035251378, https://openalex.org/W3128371468, https://openalex.org/W6677580257, https://openalex.org/W6755207826, https://openalex.org/W6774054309, https://openalex.org/W6739901393, https://openalex.org/W2962861284, https://openalex.org/W2994749257, https://openalex.org/W2963403868, https://openalex.org/W2764043458, https://openalex.org/W2101105183, https://openalex.org/W2964299589, https://openalex.org/W3101731278, https://openalex.org/W3162309234, https://openalex.org/W3006683367, https://openalex.org/W3175549063, https://openalex.org/W2963341956 |
| referenced_works_count | 25 |
| abstract_inverted_index.- | 192, 199 |
| abstract_inverted_index.a | 34, 58, 109, 119, 156, 168, 184 |
| abstract_inverted_index.1% | 174 |
| abstract_inverted_index.We | 32 |
| abstract_inverted_index.as | 61 |
| abstract_inverted_index.at | 30, 49, 72, 83 |
| abstract_inverted_index.be | 150 |
| abstract_inverted_index.in | 118, 141, 167 |
| abstract_inverted_index.is | 3, 91, 129 |
| abstract_inverted_index.it | 15, 154 |
| abstract_inverted_index.of | 112, 123, 145, 158, 172 |
| abstract_inverted_index.on | 19, 45, 86, 93 |
| abstract_inverted_index.to | 17, 64, 137, 152, 155 |
| abstract_inverted_index.GPU | 196 |
| abstract_inverted_index.HAT | 59 |
| abstract_inverted_index.The | 0, 53, 75, 89, 161 |
| abstract_inverted_index.and | 97, 197 |
| abstract_inverted_index.any | 50 |
| abstract_inverted_index.are | 78 |
| abstract_inverted_index.can | 28, 149 |
| abstract_inverted_index.for | 6, 66, 175, 187, 194, 201 |
| abstract_inverted_index.its | 11 |
| abstract_inverted_index.new | 162 |
| abstract_inverted_index.not | 130 |
| abstract_inverted_index.the | 41, 46, 62, 81, 94, 98, 106, 126, 143, 146, 179, 195, 202 |
| abstract_inverted_index.2.9s | 198 |
| abstract_inverted_index.BLEU | 120, 169 |
| abstract_inverted_index.CPU. | 203 |
| abstract_inverted_index.Nano | 96 |
| abstract_inverted_index.from | 80, 105, 132, 178 |
| abstract_inverted_index.loss | 122, 140 |
| abstract_inverted_index.that | 39 |
| abstract_inverted_index.this | 139 |
| abstract_inverted_index.time | 111 |
| abstract_inverted_index.used | 5 |
| abstract_inverted_index.uses | 57, 100 |
| abstract_inverted_index.vary | 29 |
| abstract_inverted_index.wide | 185 |
| abstract_inverted_index.with | 68, 108, 183 |
| abstract_inverted_index.7.31s | 200 |
| abstract_inverted_index.Using | 114 |
| abstract_inverted_index.after | 134 |
| abstract_inverted_index.based | 44 |
| abstract_inverted_index.makes | 14 |
| abstract_inverted_index.model | 38 |
| abstract_inverted_index.range | 186 |
| abstract_inverted_index.score | 121, 170 |
| abstract_inverted_index.space | 148, 165 |
| abstract_inverted_index.time. | 52, 74 |
| abstract_inverted_index.where | 24 |
| abstract_inverted_index.0.356s | 191 |
| abstract_inverted_index.1.526s | 193 |
| abstract_inverted_index.Jetson | 95 |
| abstract_inverted_index.design | 73, 147, 164, 181 |
| abstract_inverted_index.family | 157 |
| abstract_inverted_index.models | 177 |
| abstract_inverted_index.nature | 13 |
| abstract_inverted_index.scales | 40 |
| abstract_inverted_index.search | 65 |
| abstract_inverted_index.space, | 182 |
| abstract_inverted_index.tailor | 153 |
| abstract_inverted_index.target | 159 |
| abstract_inverted_index.tasks. | 9 |
| abstract_inverted_index.tested | 92 |
| abstract_inverted_index.widely | 4 |
| abstract_inverted_index.<1s. | 113 |
| abstract_inverted_index.because | 125 |
| abstract_inverted_index.between | 190 |
| abstract_inverted_index.dynamic | 35 |
| abstract_inverted_index.latency | 87 |
| abstract_inverted_index.machine | 7, 36 |
| abstract_inverted_index.optimal | 76 |
| abstract_inverted_index.propose | 33 |
| abstract_inverted_index.recover | 138 |
| abstract_inverted_index.reduced | 151, 163 |
| abstract_inverted_index.results | 117, 166 |
| abstract_inverted_index.sampled | 79, 103 |
| abstract_inverted_index.scaling | 189 |
| abstract_inverted_index.scratch | 133 |
| abstract_inverted_index.<1.5% | 124 |
| abstract_inverted_index.However, | 10, 136 |
| abstract_inverted_index.approach | 99 |
| abstract_inverted_index.backbone | 63 |
| abstract_inverted_index.devices, | 22 |
| abstract_inverted_index.directly | 104 |
| abstract_inverted_index.embedded | 21 |
| abstract_inverted_index.hardware | 26 |
| abstract_inverted_index.increase | 171 |
| abstract_inverted_index.original | 180 |
| abstract_inverted_index.proposed | 54 |
| abstract_inverted_index.approach, | 55 |
| abstract_inverted_index.available | 25, 47 |
| abstract_inverted_index.depending | 85 |
| abstract_inverted_index.different | 69 |
| abstract_inverted_index.hardware. | 160 |
| abstract_inverted_index.implement | 18 |
| abstract_inverted_index.inherited | 101, 115 |
| abstract_inverted_index.resources | 27, 48 |
| abstract_inverted_index.retrained | 131 |
| abstract_inverted_index.run-time, | 84 |
| abstract_inverted_index.run-time. | 31 |
| abstract_inverted_index.sampling. | 135 |
| abstract_inverted_index.switching | 110 |
| abstract_inverted_index.dimensions | 144 |
| abstract_inverted_index.particular | 51 |
| abstract_inverted_index.trade-offs | 71 |
| abstract_inverted_index.Dynamic-HAT | 90 |
| abstract_inverted_index.Transformer | 1, 42 |
| abstract_inverted_index.challenging | 16 |
| abstract_inverted_index.constrained | 20 |
| abstract_inverted_index.performance | 188 |
| abstract_inverted_index.sub-optimal | 176 |
| abstract_inverted_index.translation | 8, 37 |
| abstract_inverted_index.architecture | 2, 43 |
| abstract_inverted_index.constraints. | 88 |
| abstract_inverted_index.particularly | 23 |
| abstract_inverted_index.performance, | 142 |
| abstract_inverted_index.approximately | 173 |
| abstract_inverted_index.configuration | 128 |
| abstract_inverted_index.'Dynamic-HAT', | 56 |
| abstract_inverted_index.SubTransformer | 127 |
| abstract_inverted_index.SubTransformers | 67, 77, 102, 116 |
| abstract_inverted_index.SuperTransformer | 60, 82, 107 |
| abstract_inverted_index.accuracy-latency | 70 |
| abstract_inverted_index.resource-intensive | 12 |
| cited_by_percentile_year.max | 96 |
| cited_by_percentile_year.min | 94 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile.value | 0.63434025 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |