NeKo: Cross-Modality Post-Recognition Error Correction with Tasks-Guided Mixture-of-Experts Language Model Article Swipe
Yen‐Ting Lin
,
Chao-Han Huck Yang
,
Zhehuai Chen
,
Piotr Żelasko
,
Xuesong Yang
,
Zih-Ching Chen
,
Krishna C. Puvvada
,
Szu‐Wei Fu
,
Ke Hu
,
Jennifer L. Chiu
,
Jagadeesh Balam
,
Boris Ginsburg
,
Yu-Chiang Frank Wang
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2411.05945
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2411.05945
Construction of a general-purpose post-recognition error corrector poses a crucial question: how can we most effectively train a model on a large mixture of domain datasets? The answer would lie in learning dataset-specific features and digesting their knowledge in a single model. Previous methods achieve this by having separate correction language models, resulting in a significant increase in parameters. In this work, we present Mixture-of-Experts as a solution, highlighting that MoEs are much more than a scalability tool. We propose a Multi-Task Correction MoE, where we train the experts to become an ``expert'' of speech-to-text, language-to-text and vision-to-text datasets by learning to route each dataset's tokens to its mapped expert. Experiments on the Open ASR Leaderboard show that we explore a new state-of-the-art performance by achieving an average relative 5.0% WER reduction and substantial improvements in BLEU scores for speech and translation tasks. On zero-shot evaluation, NeKo outperforms GPT-3.5 and Claude-Opus with 15.5% to 27.6% relative WER reduction in the Hyporadise benchmark. NeKo performs competitively on grammar and post-OCR correction as a multi-task model.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2411.05945
- https://arxiv.org/pdf/2411.05945
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4404400360
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4404400360Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2411.05945Digital Object Identifier
- Title
-
NeKo: Cross-Modality Post-Recognition Error Correction with Tasks-Guided Mixture-of-Experts Language ModelWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-11-08Full publication date if available
- Authors
-
Yen‐Ting Lin, Chao-Han Huck Yang, Zhehuai Chen, Piotr Żelasko, Xuesong Yang, Zih-Ching Chen, Krishna C. Puvvada, Szu‐Wei Fu, Ke Hu, Jennifer L. Chiu, Jagadeesh Balam, Boris Ginsburg, Yu-Chiang Frank WangList of authors in order
- Landing page
-
https://arxiv.org/abs/2411.05945Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2411.05945Direct 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/2411.05945Direct OA link when available
- Concepts
-
Generative grammar, Task (project management), Natural language processing, Computer science, Artificial intelligence, Linguistics, Engineering, Philosophy, Systems engineeringTop 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/W4404400360 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2411.05945 |
| ids.doi | https://doi.org/10.48550/arxiv.2411.05945 |
| ids.openalex | https://openalex.org/W4404400360 |
| fwci | |
| type | preprint |
| title | NeKo: Cross-Modality Post-Recognition Error Correction with Tasks-Guided Mixture-of-Experts Language Model |
| 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 | 0.9948999881744385 |
| 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 | 0.9891999959945679 |
| 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/C39890363 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8083746433258057 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q36108 |
| concepts[0].display_name | Generative grammar |
| concepts[1].id | https://openalex.org/C2780451532 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6334576606750488 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q759676 |
| concepts[1].display_name | Task (project management) |
| concepts[2].id | https://openalex.org/C204321447 |
| concepts[2].level | 1 |
| concepts[2].score | 0.6161201000213623 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[2].display_name | Natural language processing |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.6134142875671387 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.46805116534233093 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C41895202 |
| concepts[5].level | 1 |
| concepts[5].score | 0.44364914298057556 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[5].display_name | Linguistics |
| concepts[6].id | https://openalex.org/C127413603 |
| concepts[6].level | 0 |
| concepts[6].score | 0.07246872782707214 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[6].display_name | Engineering |
| concepts[7].id | https://openalex.org/C138885662 |
| concepts[7].level | 0 |
| concepts[7].score | 0.04261532425880432 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[7].display_name | Philosophy |
| concepts[8].id | https://openalex.org/C201995342 |
| concepts[8].level | 1 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q682496 |
| concepts[8].display_name | Systems engineering |
| keywords[0].id | https://openalex.org/keywords/generative-grammar |
| keywords[0].score | 0.8083746433258057 |
| keywords[0].display_name | Generative grammar |
| keywords[1].id | https://openalex.org/keywords/task |
| keywords[1].score | 0.6334576606750488 |
| keywords[1].display_name | Task (project management) |
| keywords[2].id | https://openalex.org/keywords/natural-language-processing |
| keywords[2].score | 0.6161201000213623 |
| keywords[2].display_name | Natural language processing |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.6134142875671387 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.46805116534233093 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/linguistics |
| keywords[5].score | 0.44364914298057556 |
| keywords[5].display_name | Linguistics |
| keywords[6].id | https://openalex.org/keywords/engineering |
| keywords[6].score | 0.07246872782707214 |
| keywords[6].display_name | Engineering |
| keywords[7].id | https://openalex.org/keywords/philosophy |
| keywords[7].score | 0.04261532425880432 |
| keywords[7].display_name | Philosophy |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2411.05945 |
| 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/2411.05945 |
| 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/2411.05945 |
| locations[1].id | doi:10.48550/arxiv.2411.05945 |
| 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.2411.05945 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5012819966 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-7146-4687 |
| authorships[0].author.display_name | Yen‐Ting Lin |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Lin, Yen-Ting |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5020376803 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-2879-8811 |
| authorships[1].author.display_name | Chao-Han Huck Yang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Yang, Chao-Han Huck |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5002433660 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-4400-5340 |
| authorships[2].author.display_name | Zhehuai Chen |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Chen, Zhehuai |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5027217976 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-8245-0413 |
| authorships[3].author.display_name | Piotr Żelasko |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Zelasko, Piotr |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5059726557 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-8625-5044 |
| authorships[4].author.display_name | Xuesong Yang |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Yang, Xuesong |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5006382467 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Zih-Ching Chen |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Chen, Zih-Ching |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5069691915 |
| authorships[6].author.orcid | |
| authorships[6].author.display_name | Krishna C. Puvvada |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Puvvada, Krishna C |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5071471469 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-3487-8212 |
| authorships[7].author.display_name | Szu‐Wei Fu |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Fu, Szu-Wei |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5029338576 |
| authorships[8].author.orcid | https://orcid.org/0000-0002-1599-1519 |
| authorships[8].author.display_name | Ke Hu |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Hu, Ke |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5040427115 |
| authorships[9].author.orcid | https://orcid.org/0000-0001-7663-5748 |
| authorships[9].author.display_name | Jennifer L. Chiu |
| authorships[9].author_position | middle |
| authorships[9].raw_author_name | Chiu, Jun Wei |
| authorships[9].is_corresponding | False |
| authorships[10].author.id | https://openalex.org/A5040747392 |
| authorships[10].author.orcid | |
| authorships[10].author.display_name | Jagadeesh Balam |
| authorships[10].author_position | middle |
| authorships[10].raw_author_name | Balam, Jagadeesh |
| authorships[10].is_corresponding | False |
| authorships[11].author.id | https://openalex.org/A5032957280 |
| authorships[11].author.orcid | |
| authorships[11].author.display_name | Boris Ginsburg |
| authorships[11].author_position | middle |
| authorships[11].raw_author_name | Ginsburg, Boris |
| authorships[11].is_corresponding | False |
| authorships[12].author.id | https://openalex.org/A5090045508 |
| authorships[12].author.orcid | https://orcid.org/0000-0002-2333-157X |
| authorships[12].author.display_name | Yu-Chiang Frank Wang |
| authorships[12].author_position | last |
| authorships[12].raw_author_name | Wang, Yu-Chiang Frank |
| authorships[12].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/2411.05945 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-11-15T00:00:00 |
| display_name | NeKo: Cross-Modality Post-Recognition Error Correction with Tasks-Guided Mixture-of-Experts Language Model |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-12-03T23:09:05.601824 |
| 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 | 0.9948999881744385 |
| 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/W2380075625, https://openalex.org/W4390718435, https://openalex.org/W4390549206, https://openalex.org/W3137171911, https://openalex.org/W4379540039, https://openalex.org/W4237784285, https://openalex.org/W2374712251, https://openalex.org/W4383031710, https://openalex.org/W4385572368, https://openalex.org/W3204019825 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2411.05945 |
| 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/2411.05945 |
| 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/2411.05945 |
| primary_location.id | pmh:oai:arXiv.org:2411.05945 |
| 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/2411.05945 |
| 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/2411.05945 |
| publication_date | 2024-11-08 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 2, 8, 17, 20, 39, 54, 66, 75, 80, 120, 171 |
| abstract_inverted_index.In | 59 |
| abstract_inverted_index.On | 143 |
| abstract_inverted_index.We | 78 |
| abstract_inverted_index.an | 91, 126 |
| abstract_inverted_index.as | 65, 170 |
| abstract_inverted_index.by | 46, 99, 124 |
| abstract_inverted_index.in | 30, 38, 53, 57, 135, 158 |
| abstract_inverted_index.of | 1, 23, 93 |
| abstract_inverted_index.on | 19, 111, 165 |
| abstract_inverted_index.to | 89, 101, 106, 153 |
| abstract_inverted_index.we | 13, 62, 85, 118 |
| abstract_inverted_index.ASR | 114 |
| abstract_inverted_index.The | 26 |
| abstract_inverted_index.WER | 130, 156 |
| abstract_inverted_index.and | 34, 96, 132, 140, 149, 167 |
| abstract_inverted_index.are | 71 |
| abstract_inverted_index.can | 12 |
| abstract_inverted_index.for | 138 |
| abstract_inverted_index.how | 11 |
| abstract_inverted_index.its | 107 |
| abstract_inverted_index.lie | 29 |
| abstract_inverted_index.new | 121 |
| abstract_inverted_index.the | 87, 112, 159 |
| abstract_inverted_index.5.0% | 129 |
| abstract_inverted_index.BLEU | 136 |
| abstract_inverted_index.MoE, | 83 |
| abstract_inverted_index.MoEs | 70 |
| abstract_inverted_index.NeKo | 146, 162 |
| abstract_inverted_index.Open | 113 |
| abstract_inverted_index.each | 103 |
| abstract_inverted_index.more | 73 |
| abstract_inverted_index.most | 14 |
| abstract_inverted_index.much | 72 |
| abstract_inverted_index.show | 116 |
| abstract_inverted_index.than | 74 |
| abstract_inverted_index.that | 69, 117 |
| abstract_inverted_index.this | 45, 60 |
| abstract_inverted_index.with | 151 |
| abstract_inverted_index.15.5% | 152 |
| abstract_inverted_index.27.6% | 154 |
| abstract_inverted_index.error | 5 |
| abstract_inverted_index.large | 21 |
| abstract_inverted_index.model | 18 |
| abstract_inverted_index.poses | 7 |
| abstract_inverted_index.route | 102 |
| abstract_inverted_index.their | 36 |
| abstract_inverted_index.tool. | 77 |
| abstract_inverted_index.train | 16, 86 |
| abstract_inverted_index.where | 84 |
| abstract_inverted_index.work, | 61 |
| abstract_inverted_index.would | 28 |
| abstract_inverted_index.answer | 27 |
| abstract_inverted_index.become | 90 |
| abstract_inverted_index.domain | 24 |
| abstract_inverted_index.having | 47 |
| abstract_inverted_index.mapped | 108 |
| abstract_inverted_index.model. | 41, 173 |
| abstract_inverted_index.scores | 137 |
| abstract_inverted_index.single | 40 |
| abstract_inverted_index.speech | 139 |
| abstract_inverted_index.tasks. | 142 |
| abstract_inverted_index.tokens | 105 |
| abstract_inverted_index.GPT-3.5 | 148 |
| abstract_inverted_index.achieve | 44 |
| abstract_inverted_index.average | 127 |
| abstract_inverted_index.crucial | 9 |
| abstract_inverted_index.expert. | 109 |
| abstract_inverted_index.experts | 88 |
| abstract_inverted_index.explore | 119 |
| abstract_inverted_index.grammar | 166 |
| abstract_inverted_index.methods | 43 |
| abstract_inverted_index.mixture | 22 |
| abstract_inverted_index.models, | 51 |
| abstract_inverted_index.present | 63 |
| abstract_inverted_index.propose | 79 |
| abstract_inverted_index.Previous | 42 |
| abstract_inverted_index.datasets | 98 |
| abstract_inverted_index.features | 33 |
| abstract_inverted_index.increase | 56 |
| abstract_inverted_index.language | 50 |
| abstract_inverted_index.learning | 31, 100 |
| abstract_inverted_index.performs | 163 |
| abstract_inverted_index.post-OCR | 168 |
| abstract_inverted_index.relative | 128, 155 |
| abstract_inverted_index.separate | 48 |
| abstract_inverted_index.achieving | 125 |
| abstract_inverted_index.corrector | 6 |
| abstract_inverted_index.dataset's | 104 |
| abstract_inverted_index.datasets? | 25 |
| abstract_inverted_index.digesting | 35 |
| abstract_inverted_index.knowledge | 37 |
| abstract_inverted_index.question: | 10 |
| abstract_inverted_index.reduction | 131, 157 |
| abstract_inverted_index.resulting | 52 |
| abstract_inverted_index.solution, | 67 |
| abstract_inverted_index.zero-shot | 144 |
| abstract_inverted_index.Correction | 82 |
| abstract_inverted_index.Hyporadise | 160 |
| abstract_inverted_index.Multi-Task | 81 |
| abstract_inverted_index.``expert'' | 92 |
| abstract_inverted_index.benchmark. | 161 |
| abstract_inverted_index.correction | 49, 169 |
| abstract_inverted_index.multi-task | 172 |
| abstract_inverted_index.Claude-Opus | 150 |
| abstract_inverted_index.Experiments | 110 |
| abstract_inverted_index.Leaderboard | 115 |
| abstract_inverted_index.effectively | 15 |
| abstract_inverted_index.evaluation, | 145 |
| abstract_inverted_index.outperforms | 147 |
| abstract_inverted_index.parameters. | 58 |
| abstract_inverted_index.performance | 123 |
| abstract_inverted_index.scalability | 76 |
| abstract_inverted_index.significant | 55 |
| abstract_inverted_index.substantial | 133 |
| abstract_inverted_index.translation | 141 |
| abstract_inverted_index.Construction | 0 |
| abstract_inverted_index.highlighting | 68 |
| abstract_inverted_index.improvements | 134 |
| abstract_inverted_index.competitively | 164 |
| abstract_inverted_index.vision-to-text | 97 |
| abstract_inverted_index.general-purpose | 3 |
| abstract_inverted_index.speech-to-text, | 94 |
| abstract_inverted_index.dataset-specific | 32 |
| abstract_inverted_index.language-to-text | 95 |
| abstract_inverted_index.post-recognition | 4 |
| abstract_inverted_index.state-of-the-art | 122 |
| abstract_inverted_index.Mixture-of-Experts | 64 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 13 |
| citation_normalized_percentile |