{"id":"https://openalex.org/W7140086372","doi":"https://doi.org/10.18653/v1/2026.latechclfl-1.12","title":"Catalogues as Data: Interpretable NLP Pipelines for Ottoman-Turkish Bibliographies","display_name":"Catalogues as Data: Interpretable NLP Pipelines for Ottoman-Turkish Bibliographies","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140086372","doi":"https://doi.org/10.18653/v1/2026.latechclfl-1.12"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.latechclfl-1.12","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.latechclfl-1.12","pdf_url":"https://aclanthology.org/2026.latechclfl-1.12.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 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.latechclfl-1.12.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130340846","display_name":"Mark Hill","orcid":null},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark Hill","raw_affiliation_strings":["King's College London Strand , WC2R 2LS London , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King's College London Strand , WC2R 2LS London , UK","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130401794","display_name":"Ayse Bulus","orcid":null},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ayse Bulus","raw_affiliation_strings":["King's College London Strand , WC2R 2LS London , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King's College London Strand , WC2R 2LS London , UK","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130347916","display_name":"Paul Spence","orcid":null},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Paul Spence","raw_affiliation_strings":["King's College London Strand , WC2R 2LS London , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King's College London Strand , WC2R 2LS London , UK","institution_ids":["https://openalex.org/I183935753"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183935753"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31451187,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"128","last_page":"134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.391400009393692,"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"}},"topics":[{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.391400009393692,"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/T14330","display_name":"Library Science and Information Systems","score":0.09749999642372131,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.07450000196695328,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/pipeline","display_name":"Pipeline (software)","score":0.46230000257492065},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.4424999952316284},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2475000023841858},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.2386000007390976},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2159000039100647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6306999921798706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6234999895095825},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6075000166893005},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.4424999952316284},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2475000023841858},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.24310000240802765},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2386000007390976},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2159000039100647},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.21570000052452087}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2026.latechclfl-1.12","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.latechclfl-1.12","pdf_url":"https://aclanthology.org/2026.latechclfl-1.12.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 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:kclpure.kcl.ac.uk:openaire/1feed77c-8b50-425b-9ce4-983e406fa25f","is_oa":true,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/1feed77c-8b50-425b-9ce4-983e406fa25f","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.latechclfl-1.12","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.latechclfl-1.12","pdf_url":"https://aclanthology.org/2026.latechclfl-1.12.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 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320285","display_name":"King's College London","ror":"https://ror.org/0220mzb33"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140086372.pdf","grobid_xml":"https://content.openalex.org/works/W7140086372.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Bibliographies":[0],"are":[1],"both":[2],"humanities":[3],"infrastructure":[4],"and":[5,16,48,62,75,81],"historic":[6],"record.To":[7],"computationally":[8],"analyse":[9],"them,":[10],"however,":[11],"requires":[12],"implementing":[13],"complex":[14,40,115],"digitisation":[15],"standardisation":[17],"decisions.This":[18],"paper":[19],"turns":[20],"to":[21],"Seyfettin":[22],"zege's":[23],"Eski":[24],"Harflerle":[25],"Baslm":[26],"Trke":[27],"Eserler":[28],"Katalogu":[29],"as":[30],"an":[31,110],"example,":[32],"a":[33,55,59],"scanned":[34],"set":[35],"of":[36,66,88,94],"volumes":[37],"marked":[38],"by":[39,97],"page":[41],"layouts,":[42],"degraded":[43],"typography,":[44],"irregular":[45],"entry":[46],"structures,":[47],"historically":[49,114],"contingent":[50],"inconsistencies.With":[51],"this":[52],"we":[53],"present":[54],"pipeline":[56],"that":[57,102],"constructs":[58],"structured,":[60],"machine-readable,":[61],"analysable":[63],"dataset":[64],"out":[65],"the":[67],"27,000":[68],"entries":[69],"with":[70,90,105],"computer":[71],"vision,":[72],"OCR,":[73],"large":[74],"visual":[76],"language":[77],"models,":[78],"sequence-based":[79],"validation,":[80],"custom":[82],"review":[83],"tools.This":[84],"process":[85,100],"captures":[86],"97.8%":[87],"records,":[89],"remaining":[91],"cases":[92],"capable":[93],"being":[95],"addressed":[96],"targeted":[98],"review.This":[99],"demonstrates":[101],"combining":[103],"LLMs":[104],"interpretable,":[106],"review-centric":[107],"pipelines,":[108],"offers":[109],"appropriate":[111],"approach":[112],"for":[113],"bibliographic":[116],"sources.":[117]},"counts_by_year":[],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2026-03-24T00:00:00"}
