DRAG: Director-Generator Language Modelling Framework for Non-Parallel\n Author Stylized Rewriting Article Swipe
Hrituraj Singh
,
Gaurav Verma
,
Aparna Garimella
,
B. Srinivasan
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2101.11836
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2101.11836
Author stylized rewriting is the task of rewriting an input text in a\nparticular author's style. Recent works in this area have leveraged\nTransformer-based language models in a denoising autoencoder setup to generate\nauthor stylized text without relying on a parallel corpus of data. However,\nthese approaches are limited by the lack of explicit control of target\nattributes and being entirely data-driven. In this paper, we propose a\nDirector-Generator framework to rewrite content in the target author's style,\nspecifically focusing on certain target attributes. We show that our proposed\nframework works well even with a limited-sized target author corpus. Our\nexperiments on corpora consisting of relatively small-sized text authored by\nthree distinct authors show significant improvements upon existing works to\nrewrite input texts in target author's style. Our quantitative and qualitative\nanalyses further show that our model has better meaning retention and results\nin more fluent generations.\n
Related Topics
Concepts
Metadata
- Type
- preprint
- Landing Page
- http://arxiv.org/abs/2101.11836
- https://arxiv.org/pdf/2101.11836
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4287365970
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4287365970Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2101.11836Digital Object Identifier
- Title
-
DRAG: Director-Generator Language Modelling Framework for Non-Parallel\n Author Stylized RewritingWork title
- Type
-
preprintOpenAlex work type
- Publication year
-
2021Year of publication
- Publication date
-
2021-01-28Full publication date if available
- Authors
-
Hrituraj Singh, Gaurav Verma, Aparna Garimella, B. SrinivasanList of authors in order
- Landing page
-
https://arxiv.org/abs/2101.11836Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2101.11836Direct 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/2101.11836Direct OA link when available
- Concepts
-
Stylized fact, Computer science, Rewriting, Transformer, Generator (circuit theory), Style (visual arts), Artificial intelligence, Syntax, Natural language processing, Programming language, Power (physics), History, Archaeology, Macroeconomics, Economics, Quantum mechanics, Physics, VoltageTop 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/W4287365970 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2101.11836 |
| ids.openalex | https://openalex.org/W4287365970 |
| fwci | 0.0 |
| type | preprint |
| title | DRAG: Director-Generator Language Modelling Framework for Non-Parallel\n Author Stylized Rewriting |
| 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 | 0.9908000230789185 |
| 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 | 0.9894000291824341 |
| 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/T12380 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9836000204086304 |
| 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 | Authorship Attribution and Profiling |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C38935604 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8952968120574951 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q4330363 |
| concepts[0].display_name | Stylized fact |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.8030329942703247 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C154690210 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6934865117073059 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1668499 |
| concepts[2].display_name | Rewriting |
| concepts[3].id | https://openalex.org/C66322947 |
| concepts[3].level | 3 |
| concepts[3].score | 0.6474267244338989 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11658 |
| concepts[3].display_name | Transformer |
| concepts[4].id | https://openalex.org/C2780992000 |
| concepts[4].level | 3 |
| concepts[4].score | 0.5897985100746155 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q17016113 |
| concepts[4].display_name | Generator (circuit theory) |
| concepts[5].id | https://openalex.org/C2776445246 |
| concepts[5].level | 2 |
| concepts[5].score | 0.46982264518737793 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q1792644 |
| concepts[5].display_name | Style (visual arts) |
| concepts[6].id | https://openalex.org/C154945302 |
| concepts[6].level | 1 |
| concepts[6].score | 0.46885403990745544 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[6].display_name | Artificial intelligence |
| concepts[7].id | https://openalex.org/C60048249 |
| concepts[7].level | 2 |
| concepts[7].score | 0.45371872186660767 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q37437 |
| concepts[7].display_name | Syntax |
| concepts[8].id | https://openalex.org/C204321447 |
| concepts[8].level | 1 |
| concepts[8].score | 0.44129958748817444 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[8].display_name | Natural language processing |
| concepts[9].id | https://openalex.org/C199360897 |
| concepts[9].level | 1 |
| concepts[9].score | 0.3391195833683014 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[9].display_name | Programming language |
| concepts[10].id | https://openalex.org/C163258240 |
| concepts[10].level | 2 |
| concepts[10].score | 0.09657877683639526 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q25342 |
| concepts[10].display_name | Power (physics) |
| concepts[11].id | https://openalex.org/C95457728 |
| concepts[11].level | 0 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q309 |
| concepts[11].display_name | History |
| concepts[12].id | https://openalex.org/C166957645 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q23498 |
| concepts[12].display_name | Archaeology |
| concepts[13].id | https://openalex.org/C139719470 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q39680 |
| concepts[13].display_name | Macroeconomics |
| concepts[14].id | https://openalex.org/C162324750 |
| concepts[14].level | 0 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[14].display_name | Economics |
| concepts[15].id | https://openalex.org/C62520636 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[15].display_name | Quantum mechanics |
| concepts[16].id | https://openalex.org/C121332964 |
| concepts[16].level | 0 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[16].display_name | Physics |
| concepts[17].id | https://openalex.org/C165801399 |
| concepts[17].level | 2 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q25428 |
| concepts[17].display_name | Voltage |
| keywords[0].id | https://openalex.org/keywords/stylized-fact |
| keywords[0].score | 0.8952968120574951 |
| keywords[0].display_name | Stylized fact |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.8030329942703247 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/rewriting |
| keywords[2].score | 0.6934865117073059 |
| keywords[2].display_name | Rewriting |
| keywords[3].id | https://openalex.org/keywords/transformer |
| keywords[3].score | 0.6474267244338989 |
| keywords[3].display_name | Transformer |
| keywords[4].id | https://openalex.org/keywords/generator |
| keywords[4].score | 0.5897985100746155 |
| keywords[4].display_name | Generator (circuit theory) |
| keywords[5].id | https://openalex.org/keywords/style |
| keywords[5].score | 0.46982264518737793 |
| keywords[5].display_name | Style (visual arts) |
| keywords[6].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[6].score | 0.46885403990745544 |
| keywords[6].display_name | Artificial intelligence |
| keywords[7].id | https://openalex.org/keywords/syntax |
| keywords[7].score | 0.45371872186660767 |
| keywords[7].display_name | Syntax |
| keywords[8].id | https://openalex.org/keywords/natural-language-processing |
| keywords[8].score | 0.44129958748817444 |
| keywords[8].display_name | Natural language processing |
| keywords[9].id | https://openalex.org/keywords/programming-language |
| keywords[9].score | 0.3391195833683014 |
| keywords[9].display_name | Programming language |
| keywords[10].id | https://openalex.org/keywords/power |
| keywords[10].score | 0.09657877683639526 |
| keywords[10].display_name | Power (physics) |
| language | |
| locations[0].id | pmh:oai:arXiv.org:2101.11836 |
| 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/2101.11836 |
| 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/2101.11836 |
| indexed_in | arxiv |
| authorships[0].author.id | https://openalex.org/A5044442880 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-3705-120X |
| authorships[0].author.display_name | Hrituraj Singh |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Singh, Hrituraj |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5058032023 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-1894-1103 |
| authorships[1].author.display_name | Gaurav Verma |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Verma, Gaurav |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5014285077 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-3111-0686 |
| authorships[2].author.display_name | Aparna Garimella |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Garimella, Aparna |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5059650977 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-3118-5779 |
| authorships[3].author.display_name | B. Srinivasan |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Srinivasan, Balaji Vasan |
| authorships[3].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/2101.11836 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2022-07-25T00:00:00 |
| display_name | DRAG: Director-Generator Language Modelling Framework for Non-Parallel\n Author Stylized Rewriting |
| has_fulltext | False |
| 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 | 0.9908000230789185 |
| 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/W2529311304, https://openalex.org/W4248275646, https://openalex.org/W2992609826, https://openalex.org/W3124809058, https://openalex.org/W2552900035, https://openalex.org/W2162875951, https://openalex.org/W2062875858, https://openalex.org/W4380047323, https://openalex.org/W2138330538, https://openalex.org/W2046581487 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | pmh:oai:arXiv.org:2101.11836 |
| 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/2101.11836 |
| 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/2101.11836 |
| primary_location.id | pmh:oai:arXiv.org:2101.11836 |
| 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/2101.11836 |
| 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/2101.11836 |
| publication_date | 2021-01-28 |
| publication_year | 2021 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 25, 36, 86 |
| abstract_inverted_index.In | 57 |
| abstract_inverted_index.We | 77 |
| abstract_inverted_index.an | 8 |
| abstract_inverted_index.by | 45 |
| abstract_inverted_index.in | 11, 17, 24, 67, 112 |
| abstract_inverted_index.is | 3 |
| abstract_inverted_index.of | 6, 39, 48, 51, 95 |
| abstract_inverted_index.on | 35, 73, 92 |
| abstract_inverted_index.to | 29, 64 |
| abstract_inverted_index.we | 60 |
| abstract_inverted_index.Our | 116 |
| abstract_inverted_index.and | 53, 118, 129 |
| abstract_inverted_index.are | 43 |
| abstract_inverted_index.has | 125 |
| abstract_inverted_index.our | 80, 123 |
| abstract_inverted_index.the | 4, 46, 68 |
| abstract_inverted_index.area | 19 |
| abstract_inverted_index.even | 84 |
| abstract_inverted_index.have | 20 |
| abstract_inverted_index.lack | 47 |
| abstract_inverted_index.more | 131 |
| abstract_inverted_index.show | 78, 103, 121 |
| abstract_inverted_index.task | 5 |
| abstract_inverted_index.text | 10, 32, 98 |
| abstract_inverted_index.that | 79, 122 |
| abstract_inverted_index.this | 18, 58 |
| abstract_inverted_index.upon | 106 |
| abstract_inverted_index.well | 83 |
| abstract_inverted_index.with | 85 |
| abstract_inverted_index.being | 54 |
| abstract_inverted_index.data. | 40 |
| abstract_inverted_index.input | 9, 110 |
| abstract_inverted_index.model | 124 |
| abstract_inverted_index.setup | 28 |
| abstract_inverted_index.texts | 111 |
| abstract_inverted_index.works | 16, 82, 108 |
| abstract_inverted_index.Author | 0 |
| abstract_inverted_index.Recent | 15 |
| abstract_inverted_index.author | 89 |
| abstract_inverted_index.better | 126 |
| abstract_inverted_index.corpus | 38 |
| abstract_inverted_index.fluent | 132 |
| abstract_inverted_index.models | 23 |
| abstract_inverted_index.paper, | 59 |
| abstract_inverted_index.style. | 14, 115 |
| abstract_inverted_index.target | 69, 75, 88, 113 |
| abstract_inverted_index.authors | 102 |
| abstract_inverted_index.certain | 74 |
| abstract_inverted_index.content | 66 |
| abstract_inverted_index.control | 50 |
| abstract_inverted_index.corpora | 93 |
| abstract_inverted_index.corpus. | 90 |
| abstract_inverted_index.further | 120 |
| abstract_inverted_index.limited | 44 |
| abstract_inverted_index.meaning | 127 |
| abstract_inverted_index.propose | 61 |
| abstract_inverted_index.relying | 34 |
| abstract_inverted_index.rewrite | 65 |
| abstract_inverted_index.without | 33 |
| abstract_inverted_index.author's | 13, 70, 114 |
| abstract_inverted_index.authored | 99 |
| abstract_inverted_index.distinct | 101 |
| abstract_inverted_index.entirely | 55 |
| abstract_inverted_index.existing | 107 |
| abstract_inverted_index.explicit | 49 |
| abstract_inverted_index.focusing | 72 |
| abstract_inverted_index.language | 22 |
| abstract_inverted_index.parallel | 37 |
| abstract_inverted_index.stylized | 1, 31 |
| abstract_inverted_index.by\nthree | 100 |
| abstract_inverted_index.denoising | 26 |
| abstract_inverted_index.framework | 63 |
| abstract_inverted_index.retention | 128 |
| abstract_inverted_index.rewriting | 2, 7 |
| abstract_inverted_index.approaches | 42 |
| abstract_inverted_index.consisting | 94 |
| abstract_inverted_index.relatively | 96 |
| abstract_inverted_index.attributes. | 76 |
| abstract_inverted_index.autoencoder | 27 |
| abstract_inverted_index.results\nin | 130 |
| abstract_inverted_index.significant | 104 |
| abstract_inverted_index.small-sized | 97 |
| abstract_inverted_index.to\nrewrite | 109 |
| abstract_inverted_index.data-driven. | 56 |
| abstract_inverted_index.improvements | 105 |
| abstract_inverted_index.quantitative | 117 |
| abstract_inverted_index.a\nparticular | 12 |
| abstract_inverted_index.limited-sized | 87 |
| abstract_inverted_index.generations.\n | 133 |
| abstract_inverted_index.However,\nthese | 41 |
| abstract_inverted_index.Our\nexperiments | 91 |
| abstract_inverted_index.generate\nauthor | 30 |
| abstract_inverted_index.target\nattributes | 52 |
| abstract_inverted_index.proposed\nframework | 81 |
| abstract_inverted_index.style,\nspecifically | 71 |
| abstract_inverted_index.a\nDirector-Generator | 62 |
| abstract_inverted_index.qualitative\nanalyses | 119 |
| abstract_inverted_index.leveraged\nTransformer-based | 21 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.8500000238418579 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile.value | 0.2471753 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |