Efficient Text Style Transfer Through Robust Masked Language Model and Iterative Inference Article Swipe
Osama Subhani Khan
,
Naima Iltaf
,
Usman Zia
,
Rabia Latif
,
Nor Shahida Mohd Jamail
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.1109/access.2024.3501320
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.1109/access.2024.3501320
Emergence of Large Language Models (LLMs) have prompted researchers to exploit the abilities of such models for text style transfer (TST). However, these models are prone to hallucinations and suffer from problems of manually crafting prompts and high computation requirements. The purpose of TST is to edit text sequences so that their style is changed without hindering the meaning of their content. Owing to the scarcity of parallel data, existing approaches rely on various strategies to identify and replace style attributes or to edit a given sequence as a whole. Successful style transfer should be fluent and reflect original content. To address these challenges, we propose a novel technique leveraging explanations of prompt-free few-shot contrastive learning based lightweight classifier. First, we create a style-independent corpus of target style sequences by masking out style attributes and train a generator with masked language modeling objective that learns to predict target style tokens. Then, we apply an iterative mechanism to mask source style sequences and predict target style attributes until style is transferred gauged by a pre-trained evaluator model. We conduct experiments on two real world widely used product reviews sentiment datasets on both polarities, i.e., positive to negative and negative to positive. Comparison with various prompt-based as well as unsupervised learning based methods demonstrate state-of-the-art performance of our approach.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1109/access.2024.3501320
- OA Status
- gold
- References
- 63
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4404469468
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4404469468Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1109/access.2024.3501320Digital Object Identifier
- Title
-
Efficient Text Style Transfer Through Robust Masked Language Model and Iterative InferenceWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-01-01Full publication date if available
- Authors
-
Osama Subhani Khan, Naima Iltaf, Usman Zia, Rabia Latif, Nor Shahida Mohd JamailList of authors in order
- Landing page
-
https://doi.org/10.1109/access.2024.3501320Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.1109/access.2024.3501320Direct OA link when available
- Concepts
-
Computer science, Inference, Style (visual arts), Natural language processing, Artificial intelligence, Language model, Transfer (computing), History, Parallel computing, ArchaeologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
63Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4404469468 |
|---|---|
| doi | https://doi.org/10.1109/access.2024.3501320 |
| ids.doi | https://doi.org/10.1109/access.2024.3501320 |
| ids.openalex | https://openalex.org/W4404469468 |
| fwci | 0.0 |
| type | article |
| title | Efficient Text Style Transfer Through Robust Masked Language Model and Iterative Inference |
| biblio.issue | |
| biblio.volume | 12 |
| biblio.last_page | 182373 |
| biblio.first_page | 182353 |
| 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 | 0.9994000196456909 |
| 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 | 0.9987999796867371 |
| 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 |
| topics[2].id | https://openalex.org/T10201 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9972000122070312 |
| 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 | Speech Recognition and Synthesis |
| is_xpac | False |
| apc_list.value | 1850 |
| apc_list.currency | USD |
| apc_list.value_usd | 1850 |
| apc_paid.value | 1850 |
| apc_paid.currency | USD |
| apc_paid.value_usd | 1850 |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7524316906929016 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C2776214188 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6111034750938416 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q408386 |
| concepts[1].display_name | Inference |
| concepts[2].id | https://openalex.org/C2776445246 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5678815841674805 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1792644 |
| concepts[2].display_name | Style (visual arts) |
| concepts[3].id | https://openalex.org/C204321447 |
| concepts[3].level | 1 |
| concepts[3].score | 0.5308129787445068 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[3].display_name | Natural language processing |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.48817378282546997 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C137293760 |
| concepts[5].level | 2 |
| concepts[5].score | 0.4259340167045593 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q3621696 |
| concepts[5].display_name | Language model |
| concepts[6].id | https://openalex.org/C2776175482 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4200212359428406 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q1195816 |
| concepts[6].display_name | Transfer (computing) |
| concepts[7].id | https://openalex.org/C95457728 |
| concepts[7].level | 0 |
| concepts[7].score | 0.0 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q309 |
| concepts[7].display_name | History |
| concepts[8].id | https://openalex.org/C173608175 |
| concepts[8].level | 1 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q232661 |
| concepts[8].display_name | Parallel computing |
| concepts[9].id | https://openalex.org/C166957645 |
| concepts[9].level | 1 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q23498 |
| concepts[9].display_name | Archaeology |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7524316906929016 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/inference |
| keywords[1].score | 0.6111034750938416 |
| keywords[1].display_name | Inference |
| keywords[2].id | https://openalex.org/keywords/style |
| keywords[2].score | 0.5678815841674805 |
| keywords[2].display_name | Style (visual arts) |
| keywords[3].id | https://openalex.org/keywords/natural-language-processing |
| keywords[3].score | 0.5308129787445068 |
| keywords[3].display_name | Natural language processing |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.48817378282546997 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/language-model |
| keywords[5].score | 0.4259340167045593 |
| keywords[5].display_name | Language model |
| keywords[6].id | https://openalex.org/keywords/transfer |
| keywords[6].score | 0.4200212359428406 |
| keywords[6].display_name | Transfer (computing) |
| language | en |
| locations[0].id | doi:10.1109/access.2024.3501320 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S2485537415 |
| locations[0].source.issn | 2169-3536 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 2169-3536 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | True |
| locations[0].source.display_name | IEEE Access |
| locations[0].source.host_organization | https://openalex.org/P4310319808 |
| locations[0].source.host_organization_name | Institute of Electrical and Electronics Engineers |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310319808 |
| locations[0].source.host_organization_lineage_names | Institute of Electrical and Electronics Engineers |
| locations[0].license | cc-by |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | IEEE Access |
| locations[0].landing_page_url | https://doi.org/10.1109/access.2024.3501320 |
| locations[1].id | pmh:oai:doaj.org/article:98ea44a3720e4846a6523b2be1733108 |
| locations[1].is_oa | False |
| locations[1].source.id | https://openalex.org/S4306401280 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | False |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | DOAJ (DOAJ: Directory of Open Access Journals) |
| locations[1].source.host_organization | |
| locations[1].source.host_organization_name | |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | submittedVersion |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | IEEE Access, Vol 12, Pp 182353-182373 (2024) |
| locations[1].landing_page_url | https://doaj.org/article/98ea44a3720e4846a6523b2be1733108 |
| indexed_in | crossref, doaj |
| authorships[0].author.id | https://openalex.org/A5024743587 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-2145-6731 |
| authorships[0].author.display_name | Osama Subhani Khan |
| authorships[0].affiliations[0].raw_affiliation_string | National University of Science and Technology, Islamabad, Pakistan |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Osama Subhani Khan |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | National University of Science and Technology, Islamabad, Pakistan |
| authorships[1].author.id | https://openalex.org/A5065396147 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-5392-5187 |
| authorships[1].author.display_name | Naima Iltaf |
| authorships[1].affiliations[0].raw_affiliation_string | National University of Science and Technology, Islamabad, Pakistan |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Naima Iltaf |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | National University of Science and Technology, Islamabad, Pakistan |
| authorships[2].author.id | https://openalex.org/A5114684108 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-0522-8939 |
| authorships[2].author.display_name | Usman Zia |
| authorships[2].affiliations[0].raw_affiliation_string | National University of Science and Technology, Islamabad, Pakistan |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Usman Zia |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | National University of Science and Technology, Islamabad, Pakistan |
| authorships[3].author.id | https://openalex.org/A5076524479 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-5304-5948 |
| authorships[3].author.display_name | Rabia Latif |
| authorships[3].countries | SA |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I142024983 |
| authorships[3].affiliations[0].raw_affiliation_string | Artificial Intelligence and Data Analytics Laboratory, College of Computer and Information Sciences (CCIS), Prince Sultan University, Riyadh, Saudi Arabia |
| authorships[3].institutions[0].id | https://openalex.org/I142024983 |
| authorships[3].institutions[0].ror | https://ror.org/053mqrf26 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I142024983 |
| authorships[3].institutions[0].country_code | SA |
| authorships[3].institutions[0].display_name | Prince Sultan University |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Rabia Latif |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Artificial Intelligence and Data Analytics Laboratory, College of Computer and Information Sciences (CCIS), Prince Sultan University, Riyadh, Saudi Arabia |
| authorships[4].author.id | https://openalex.org/A5052880936 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-0392-6506 |
| authorships[4].author.display_name | Nor Shahida Mohd Jamail |
| authorships[4].countries | SA |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I142024983 |
| authorships[4].affiliations[0].raw_affiliation_string | Artificial Intelligence and Data Analytics Laboratory, College of Computer and Information Sciences (CCIS), Prince Sultan University, Riyadh, Saudi Arabia |
| authorships[4].institutions[0].id | https://openalex.org/I142024983 |
| authorships[4].institutions[0].ror | https://ror.org/053mqrf26 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I142024983 |
| authorships[4].institutions[0].country_code | SA |
| authorships[4].institutions[0].display_name | Prince Sultan University |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Nor Shahida Mohd Jamail |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | Artificial Intelligence and Data Analytics Laboratory, College of Computer and Information Sciences (CCIS), Prince Sultan University, Riyadh, Saudi Arabia |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.1109/access.2024.3501320 |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Efficient Text Style Transfer Through Robust Masked Language Model and Iterative Inference |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| 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 | 0.9994000196456909 |
| 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/W2356229341, https://openalex.org/W2349768204, https://openalex.org/W2055243143, https://openalex.org/W4313326281, https://openalex.org/W574867512, https://openalex.org/W2387271333, https://openalex.org/W581389233, https://openalex.org/W2361120309, https://openalex.org/W632157940, https://openalex.org/W2387981414 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | doi:10.1109/access.2024.3501320 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S2485537415 |
| best_oa_location.source.issn | 2169-3536 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 2169-3536 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | True |
| best_oa_location.source.display_name | IEEE Access |
| best_oa_location.source.host_organization | https://openalex.org/P4310319808 |
| best_oa_location.source.host_organization_name | Institute of Electrical and Electronics Engineers |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310319808 |
| best_oa_location.source.host_organization_lineage_names | Institute of Electrical and Electronics Engineers |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | IEEE Access |
| best_oa_location.landing_page_url | https://doi.org/10.1109/access.2024.3501320 |
| primary_location.id | doi:10.1109/access.2024.3501320 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S2485537415 |
| primary_location.source.issn | 2169-3536 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 2169-3536 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | True |
| primary_location.source.display_name | IEEE Access |
| primary_location.source.host_organization | https://openalex.org/P4310319808 |
| primary_location.source.host_organization_name | Institute of Electrical and Electronics Engineers |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310319808 |
| primary_location.source.host_organization_lineage_names | Institute of Electrical and Electronics Engineers |
| primary_location.license | cc-by |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | IEEE Access |
| primary_location.landing_page_url | https://doi.org/10.1109/access.2024.3501320 |
| publication_date | 2024-01-01 |
| publication_year | 2024 |
| referenced_works | https://openalex.org/W4391136507, https://openalex.org/W4387886075, https://openalex.org/W4391808470, https://openalex.org/W3197754201, https://openalex.org/W4205635927, https://openalex.org/W4283274728, https://openalex.org/W4221161867, https://openalex.org/W3033129824, https://openalex.org/W6810281718, https://openalex.org/W6800739994, https://openalex.org/W6839758063, https://openalex.org/W6790369299, https://openalex.org/W4224937935, https://openalex.org/W6776233261, https://openalex.org/W4391303784, https://openalex.org/W6859192988, https://openalex.org/W3096831136, https://openalex.org/W6762900673, https://openalex.org/W4380988784, https://openalex.org/W4388159246, https://openalex.org/W4399768623, https://openalex.org/W6837789219, https://openalex.org/W2516809705, https://openalex.org/W6749963372, https://openalex.org/W6685053522, https://openalex.org/W4297971002, https://openalex.org/W6795619744, https://openalex.org/W6749343999, https://openalex.org/W6796596844, https://openalex.org/W3178287460, https://openalex.org/W4309797153, https://openalex.org/W6853565858, https://openalex.org/W6802539667, https://openalex.org/W3013520104, https://openalex.org/W2964529779, https://openalex.org/W6855366245, https://openalex.org/W6838847921, https://openalex.org/W6839078283, https://openalex.org/W6811129797, https://openalex.org/W6853526537, https://openalex.org/W6849269517, https://openalex.org/W2122410182, https://openalex.org/W6861783185, https://openalex.org/W4404782964, https://openalex.org/W6843727531, https://openalex.org/W6841358531, https://openalex.org/W6852770016, https://openalex.org/W2965373594, https://openalex.org/W4283168218, https://openalex.org/W2965033324, https://openalex.org/W6781243300, https://openalex.org/W6738394178, https://openalex.org/W2970562804, https://openalex.org/W2998659916, https://openalex.org/W6794834816, https://openalex.org/W6636915900, https://openalex.org/W6679855610, https://openalex.org/W4392089979, https://openalex.org/W2612690371, https://openalex.org/W2559655401, https://openalex.org/W4212774754, https://openalex.org/W4226399820, https://openalex.org/W4296959557 |
| referenced_works_count | 63 |
| abstract_inverted_index.a | 84, 88, 106, 122, 136, 172 |
| abstract_inverted_index.To | 100 |
| abstract_inverted_index.We | 176 |
| abstract_inverted_index.an | 153 |
| abstract_inverted_index.as | 87, 204, 206 |
| abstract_inverted_index.be | 94 |
| abstract_inverted_index.by | 129, 171 |
| abstract_inverted_index.is | 44, 53, 168 |
| abstract_inverted_index.of | 1, 13, 32, 42, 59, 66, 111, 125, 214 |
| abstract_inverted_index.on | 72, 179, 189 |
| abstract_inverted_index.or | 81 |
| abstract_inverted_index.so | 49 |
| abstract_inverted_index.to | 9, 26, 45, 63, 75, 82, 145, 156, 194, 198 |
| abstract_inverted_index.we | 104, 120, 151 |
| abstract_inverted_index.TST | 43 |
| abstract_inverted_index.The | 40 |
| abstract_inverted_index.and | 28, 36, 77, 96, 134, 161, 196 |
| abstract_inverted_index.are | 24 |
| abstract_inverted_index.for | 16 |
| abstract_inverted_index.our | 215 |
| abstract_inverted_index.out | 131 |
| abstract_inverted_index.the | 11, 57, 64 |
| abstract_inverted_index.two | 180 |
| abstract_inverted_index.both | 190 |
| abstract_inverted_index.edit | 46, 83 |
| abstract_inverted_index.from | 30 |
| abstract_inverted_index.have | 6 |
| abstract_inverted_index.high | 37 |
| abstract_inverted_index.mask | 157 |
| abstract_inverted_index.real | 181 |
| abstract_inverted_index.rely | 71 |
| abstract_inverted_index.such | 14 |
| abstract_inverted_index.text | 17, 47 |
| abstract_inverted_index.that | 50, 143 |
| abstract_inverted_index.used | 184 |
| abstract_inverted_index.well | 205 |
| abstract_inverted_index.with | 138, 201 |
| abstract_inverted_index.Large | 2 |
| abstract_inverted_index.Owing | 62 |
| abstract_inverted_index.Then, | 150 |
| abstract_inverted_index.apply | 152 |
| abstract_inverted_index.based | 116, 209 |
| abstract_inverted_index.data, | 68 |
| abstract_inverted_index.given | 85 |
| abstract_inverted_index.i.e., | 192 |
| abstract_inverted_index.novel | 107 |
| abstract_inverted_index.prone | 25 |
| abstract_inverted_index.style | 18, 52, 79, 91, 127, 132, 148, 159, 164, 167 |
| abstract_inverted_index.their | 51, 60 |
| abstract_inverted_index.these | 22, 102 |
| abstract_inverted_index.train | 135 |
| abstract_inverted_index.until | 166 |
| abstract_inverted_index.world | 182 |
| abstract_inverted_index.(LLMs) | 5 |
| abstract_inverted_index.(TST). | 20 |
| abstract_inverted_index.First, | 119 |
| abstract_inverted_index.Models | 4 |
| abstract_inverted_index.corpus | 124 |
| abstract_inverted_index.create | 121 |
| abstract_inverted_index.fluent | 95 |
| abstract_inverted_index.gauged | 170 |
| abstract_inverted_index.learns | 144 |
| abstract_inverted_index.masked | 139 |
| abstract_inverted_index.model. | 175 |
| abstract_inverted_index.models | 15, 23 |
| abstract_inverted_index.should | 93 |
| abstract_inverted_index.source | 158 |
| abstract_inverted_index.suffer | 29 |
| abstract_inverted_index.target | 126, 147, 163 |
| abstract_inverted_index.whole. | 89 |
| abstract_inverted_index.widely | 183 |
| abstract_inverted_index.address | 101 |
| abstract_inverted_index.changed | 54 |
| abstract_inverted_index.conduct | 177 |
| abstract_inverted_index.exploit | 10 |
| abstract_inverted_index.masking | 130 |
| abstract_inverted_index.meaning | 58 |
| abstract_inverted_index.methods | 210 |
| abstract_inverted_index.predict | 146, 162 |
| abstract_inverted_index.product | 185 |
| abstract_inverted_index.prompts | 35 |
| abstract_inverted_index.propose | 105 |
| abstract_inverted_index.purpose | 41 |
| abstract_inverted_index.reflect | 97 |
| abstract_inverted_index.replace | 78 |
| abstract_inverted_index.reviews | 186 |
| abstract_inverted_index.tokens. | 149 |
| abstract_inverted_index.various | 73, 202 |
| abstract_inverted_index.without | 55 |
| abstract_inverted_index.However, | 21 |
| abstract_inverted_index.Language | 3 |
| abstract_inverted_index.content. | 61, 99 |
| abstract_inverted_index.crafting | 34 |
| abstract_inverted_index.datasets | 188 |
| abstract_inverted_index.existing | 69 |
| abstract_inverted_index.few-shot | 113 |
| abstract_inverted_index.identify | 76 |
| abstract_inverted_index.language | 140 |
| abstract_inverted_index.learning | 115, 208 |
| abstract_inverted_index.manually | 33 |
| abstract_inverted_index.modeling | 141 |
| abstract_inverted_index.negative | 195, 197 |
| abstract_inverted_index.original | 98 |
| abstract_inverted_index.parallel | 67 |
| abstract_inverted_index.positive | 193 |
| abstract_inverted_index.problems | 31 |
| abstract_inverted_index.prompted | 7 |
| abstract_inverted_index.scarcity | 65 |
| abstract_inverted_index.sequence | 86 |
| abstract_inverted_index.transfer | 19, 92 |
| abstract_inverted_index.Emergence | 0 |
| abstract_inverted_index.abilities | 12 |
| abstract_inverted_index.approach. | 216 |
| abstract_inverted_index.evaluator | 174 |
| abstract_inverted_index.generator | 137 |
| abstract_inverted_index.hindering | 56 |
| abstract_inverted_index.iterative | 154 |
| abstract_inverted_index.mechanism | 155 |
| abstract_inverted_index.objective | 142 |
| abstract_inverted_index.positive. | 199 |
| abstract_inverted_index.sentiment | 187 |
| abstract_inverted_index.sequences | 48, 128, 160 |
| abstract_inverted_index.technique | 108 |
| abstract_inverted_index.Comparison | 200 |
| abstract_inverted_index.Successful | 90 |
| abstract_inverted_index.approaches | 70 |
| abstract_inverted_index.attributes | 80, 133, 165 |
| abstract_inverted_index.leveraging | 109 |
| abstract_inverted_index.strategies | 74 |
| abstract_inverted_index.challenges, | 103 |
| abstract_inverted_index.classifier. | 118 |
| abstract_inverted_index.computation | 38 |
| abstract_inverted_index.contrastive | 114 |
| abstract_inverted_index.demonstrate | 211 |
| abstract_inverted_index.experiments | 178 |
| abstract_inverted_index.lightweight | 117 |
| abstract_inverted_index.performance | 213 |
| abstract_inverted_index.polarities, | 191 |
| abstract_inverted_index.pre-trained | 173 |
| abstract_inverted_index.prompt-free | 112 |
| abstract_inverted_index.researchers | 8 |
| abstract_inverted_index.transferred | 169 |
| abstract_inverted_index.explanations | 110 |
| abstract_inverted_index.prompt-based | 203 |
| abstract_inverted_index.unsupervised | 207 |
| abstract_inverted_index.requirements. | 39 |
| abstract_inverted_index.hallucinations | 27 |
| abstract_inverted_index.state-of-the-art | 212 |
| abstract_inverted_index.style-independent | 123 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 5 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.6499999761581421 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile.value | 0.22755097 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |