{"id":"https://openalex.org/W6889820286","doi":"https://doi.org/10.26083/tuprints-00028905","title":"InvBERT: Reconstructing Text from Contextualized Word Embeddings by inverting the BERT pipeline","display_name":"InvBERT: Reconstructing Text from Contextualized Word Embeddings by inverting the BERT pipeline","publication_year":2021,"publication_date":"2021-09-21","ids":{"openalex":"https://openalex.org/W6889820286","doi":"https://doi.org/10.26083/tuprints-00028905"},"language":"en","primary_location":{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:153133","doi":null,"is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/view/person/Kugler=3AKai=3A=3A.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Artikel"},"volume":null,"type":"article","indexed_in":["arxiv","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://tuprints.ulb.tu-darmstadt.de/28905/2/jcls-3572-kugler.xml","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004261300","display_name":"Kai Kugler","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kugler, Kai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"M\u00fcnker, Simon","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M\u00fcnker, Simon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"H\u00f6hmann, Johannes","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"H\u00f6hmann, Johannes","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5000758128","display_name":"Achim Rettinger","orcid":"https://orcid.org/0000-0003-4950-1167","observed_orcids":["https://orcid.org/0000-0003-4950-1167"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rettinger, Achim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.2658482,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7074999809265137,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7074999809265137,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.1817999929189682,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.019999999552965164,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/textual-reconstruction","display_name":"textual reconstruction","score":0.6439999938011169},{"id":"https://openalex.org/keywords/bert","display_name":"BERT","score":0.7649999856948853},{"id":"https://openalex.org/keywords/contextualized-word-embeddings","display_name":"contextual word embeddings","score":0.8040000200271606},{"id":"https://openalex.org/keywords/transformer-encoder","display_name":"Transformer encoder","score":0.5260000228881836},{"id":"https://openalex.org/keywords/computational-literary-studies","display_name":"computational literary studies","score":0.6100000143051147},{"id":"https://openalex.org/keywords/digital-humanities","display_name":"digital humanities","score":0.5289999842643738}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7838000059127808},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.767300009727478},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7429999709129333},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7160000205039978},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6607999801635742},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5989000201225281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5026000142097473},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36480000615119934},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C18599908","wikidata":"https://www.wikidata.org/wiki/Q1196904","display_name":"Electronic publishing","level":3,"score":0.2858999967575073},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25380000472068787}],"mesh":[],"locations_count":8,"locations":[{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:153133","doi":null,"is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/view/person/Kugler=3AKai=3A=3A.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Artikel"},{"id":"pmh:oai:tuprints.ulb.tu-darmstadt.de:28905","doi":null,"is_oa":true,"landing_page_url":"https://tuprints.ulb.tu-darmstadt.de/28905/2/jcls-3572-kugler.xml","pdf_url":null,"source":{"id":"https://openalex.org/S4306401590","display_name":"Technischen Universit\u00e4t Darmstadt","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:arXiv.org:2109.10104","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.10104","pdf_url":"https://arxiv.org/pdf/2109.10104","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:df9ac020c6d148ad9a8ac8e5607ab8d1","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/df9ac020c6d148ad9a8ac8e5607ab8d1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Computational Literary Studies, Vol 2, Iss 1 (2024)","raw_type":"article"},{"id":"pmh:oai:tuprints.ulb.tu-darmstadt.de:tuda/12890","doi":null,"is_oa":false,"landing_page_url":"https://doi.org/10.26083/tuprints-00028905","pdf_url":null,"source":{"id":"https://openalex.org/S4306401590","display_name":"Technischen Universit\u00e4t Darmstadt","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.48550/arxiv.2109.10104","doi":"https://doi.org/10.48550/arxiv.2109.10104","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2109.10104","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.48694/jcls.3572","doi":"https://doi.org/10.48694/jcls.3572","is_oa":true,"landing_page_url":"https://doi.org/10.48694/jcls.3572","pdf_url":null,"source":{"id":"https://openalex.org/S7407061332","display_name":"Journal of Computational Literary Studies","issn_l":"2940-1348","issn":["2940-1348"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj","jufo-1","norway-1","vabb-shw"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"JournalArticle"},{"id":"doi:10.26083/tuprints-00028905","doi":"https://doi.org/10.26083/tuprints-00028905","is_oa":true,"landing_page_url":"https://doi.org/10.26083/tuprints-00028905","pdf_url":null,"source":{"id":"https://openalex.org/S4306401590","display_name":"Technischen Universit\u00e4t Darmstadt","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:tuprints.ulb.tu-darmstadt.de:28905","doi":null,"is_oa":true,"landing_page_url":"https://tuprints.ulb.tu-darmstadt.de/28905/2/jcls-3572-kugler.xml","pdf_url":null,"source":{"id":"https://openalex.org/S4306401590","display_name":"Technischen Universit\u00e4t Darmstadt","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.8501836061477661,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Digital":[0],"Humanities":[1],"and":[2,131],"Computational":[3],"Literary":[4],"Studies":[5],"apply":[6],"text":[7,128],"mining":[8],"methods":[9,76],"to":[10,33,146,168,171,180],"investigate":[11],"literature.":[12],"Such":[13],"automated":[14],"approaches":[15],"enable":[16],"quantitative":[17],"studies":[18],"on":[19,98],"large":[20],"corpora":[21],"which":[22],"would":[23],"not":[24,107,142],"be":[25],"feasible":[26,130],"by":[27,83],"manual":[28],"inspection":[29],"alone.":[30],"However,":[31,112],"due":[32],"copyright":[34,182],"restrictions,":[35],"the":[36,71,109,122,125,135,152,160],"availability":[37],"of":[38,73,124,137],"relevant":[39],"digitized":[40],"literary":[41],"works":[42],"is":[43,141,163],"limited.":[44],"Derived":[45],"Text":[46],"Formats":[47],"(DTFs)":[48],"have":[49],"been":[50],"proposed":[51],"as":[52,154],"a":[53,62,155,173,176],"solution.":[54],"Here,":[55],"textual":[56],"materials":[57],"are":[58,67,87],"transformed":[59],"in":[60,113,134],"such":[61],"way":[63],"that":[64,70,118,150],"copyright-critical":[65],"features":[66],"removed,":[68],"but":[69],"use":[72],"certain":[74,120],"analytical":[75,100],"remains":[77],"possible.":[78],"Contextualized":[79],"word":[80],"embeddings":[81,162],"produced":[82],"transformer-encoders":[84],"(like":[85],"BERT)":[86],"promising":[88],"candidates":[89],"for":[90,95],"DTFs":[91],"because":[92],"they":[93],"allow":[94],"state-of-the-art":[96],"performance":[97],"various":[99],"tasks":[101],"and,":[102],"at":[103],"first":[104],"sight,":[105],"do":[106],"disclose":[108],"original":[110,126],"text.":[111],"this":[114],"paper":[115],"we":[116],"demonstrate":[117],"under":[119],"conditions":[121],"reconstruction":[123,177],"copyrighted":[127],"becomes":[129],"its":[132],"publication":[133],"form":[136],"contextualized":[138,161],"token":[139],"representations":[140],"safe.":[143],"Our":[144],"attempts":[145],"invert":[147],"BERT":[148],"suggest,":[149],"publishing":[151],"encoder":[153],"black":[156],"box":[157],"together":[158],"with":[159,175],"critical,":[164],"since":[165],"it":[166],"allows":[167],"generate":[169],"data":[170],"train":[172],"decoder":[174],"accuracy":[178],"sufficient":[179],"violate":[181],"laws.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}
