{"id":"https://openalex.org/W7166813809","doi":"https://doi.org/10.18653/v1/2026.acl-long.2149","title":"Overcoming Copyright Barriers in Corpus Distribution Through Non-Reversible Hashing","display_name":"Overcoming Copyright Barriers in Corpus Distribution Through Non-Reversible Hashing","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166813809","doi":"https://doi.org/10.18653/v1/2026.acl-long.2149"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.2149","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2149","pdf_url":"https://aclanthology.org/2026.acl-long.2149.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.2149.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074047913","display_name":"Arthur Amalvy","orcid":"https://orcid.org/0000-0003-4629-0923"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arthur Amalvy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031476990","display_name":"Vincent Labatut","orcid":"https://orcid.org/0000-0002-2619-2835"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent Labatut","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074844950","display_name":"Xavier Bost","orcid":"https://orcid.org/0000-0002-5624-8721"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xavier Bost","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139842648","display_name":"Hen-Hsen Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hen-Hsen Huang","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":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86097676,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"46329","last_page":"46345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.15189999341964722,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.15189999341964722,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.11810000240802765,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.05810000002384186,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.45350000262260437},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.3896999955177307},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.3174999952316284},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.28040000796318054},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.274399995803833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6398000121116638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4699999988079071},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.45350000262260437},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3237999975681305},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2930000126361847},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27570000290870667},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.2149","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2149","pdf_url":"https://aclanthology.org/2026.acl-long.2149.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.2149","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2149","pdf_url":"https://aclanthology.org/2026.acl-long.2149.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2546293981","display_name":null,"funder_award_id":"236d-1120205","funder_id":"https://openalex.org/F4320321041","funder_display_name":"Academia Sinica"}],"funders":[{"id":"https://openalex.org/F4320321041","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784"},{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166813809.pdf","grobid_xml":"https://content.openalex.org/works/W7166813809.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"annotated":[1],"corpora":[2,24],"are":[3,17,25],"crucial":[4],"in":[5,35,38,67,96,112],"the":[6,30,36,39,56,65,76,83,88,102,113,116,121,151,154,161],"field":[7],"of":[8,32,41,58,75,115,132,147,171],"natural":[9],"language":[10],"processing":[11],"(NLP),":[12],"those":[13],"containing":[14],"copyrighted":[15,59,117],"material":[16],"difficult":[18],"to":[19,27,51,92,98,101,109,141,145,160],"exchange":[20],"among":[21],"researchers.Yet,":[22],"such":[23],"necessary":[26],"fully":[28],"represent":[29],"diversity":[31],"data":[33,118],"found":[34],"wild":[37],"context":[40],"NLP":[42],"tasks.We":[43],"tackle":[44],"this":[45],"issue":[46],"by":[47,120],"proposing":[48],"a":[49,71,168],"method":[50,106,138],"lawfully":[52],"and":[53,86],"publicly":[54,165],"share":[55],"annotations":[57,66],"literary":[60],"texts.The":[61],"corpus":[62,79,162],"creator":[63],"shares":[64],"clear,":[68],"along":[69],"with":[70],"non-reversible":[72],"hashed":[73],"version":[74,114,156],"source":[77,84],"material.The":[78],"user":[80,155],"must":[81],"own":[82,94],"material,":[85],"apply":[87],"same":[89],"hash":[90],"function":[91],"their":[93],"tokens,":[95],"order":[97],"match":[99],"them":[100],"shared":[103],"annotations.Crucially,":[104],"our":[105,137,172],"is":[107,139,157],"robust":[108],"reasonable":[110],"divergences":[111],"owned":[119],"user.As":[122],"an":[123],"illustration,":[124],"we":[125],"present":[126],"alignment":[127],"experiments":[128],"on":[129,150],"different":[130],"editions":[131],"novels.Our":[133],"results":[134],"show":[135],"that":[136],"able":[140],"correctly":[142],"align":[143],"98.7":[144],"99.79%":[146],"tokens":[148],"depending":[149],"novel,":[152],"provided":[153],"sufficiently":[158],"close":[159],"creator's":[163],"version.We":[164],"release":[166],"novelshare,":[167],"Python":[169],"implementation":[170],"method.":[173]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
