{"id":"https://openalex.org/W4383176197","doi":"https://doi.org/10.5281/zenodo.8107808","title":"Digital Humanities Applications of spaCy's Span Categorizer","display_name":"Digital Humanities Applications of spaCy's Span Categorizer","publication_year":2023,"publication_date":"2023-06-30","ids":{"openalex":"https://openalex.org/W4383176197","doi":"https://doi.org/10.5281/zenodo.8107808"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.8107808","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.8107808","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"type":"paratext","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.8107808","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047556774","display_name":"Adriane Boyd","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Boyd, Adriane","raw_affiliation_strings":["ExplosionAI"],"affiliations":[{"raw_affiliation_string":"ExplosionAI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108669016","display_name":"A. Kadar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"K\u00e1d\u00e1r, \u00c1kos","raw_affiliation_strings":["ExplosionAI"],"affiliations":[{"raw_affiliation_string":"ExplosionAI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071556828","display_name":"Andrew Janco","orcid":"https://orcid.org/0000-0002-8872-9474"},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Janco, Andrew","raw_affiliation_strings":["University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035939625","display_name":"David Lassner","orcid":"https://orcid.org/0000-0001-9013-0834"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lassner, David","raw_affiliation_strings":["TU Berlin"],"affiliations":[{"raw_affiliation_string":"TU Berlin","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002807953","display_name":"Nick Budak","orcid":"https://orcid.org/0000-0002-4542-0899"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Budak, Nick","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075022301","display_name":"Toma Tasovac","orcid":"https://orcid.org/0000-0002-3919-993X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tasovac, Toma","raw_affiliation_strings":["DARIAH"],"affiliations":[{"raw_affiliation_string":"DARIAH","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090624459","display_name":"Natalia Ermolaev","orcid":"https://orcid.org/0000-0002-0984-7799"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ermolaev, Natalia","raw_affiliation_strings":["Princeton University"],"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046186276","display_name":"Jajwalya Karajgikar","orcid":null},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karajgikar, Jajwalya","raw_affiliation_strings":["University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5047556774"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07079805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8292999863624573,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.8292999863624573,"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":0.8216999769210815,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/span","display_name":"Span (engineering)","score":0.6065806150436401},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5097381472587585},{"id":"https://openalex.org/keywords/humanities","display_name":"Humanities","score":0.4515135586261749},{"id":"https://openalex.org/keywords/digital-humanities","display_name":"Digital humanities","score":0.4316457211971283},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2360636293888092},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.21046742796897888},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.1995747685432434},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.0834067165851593}],"concepts":[{"id":"https://openalex.org/C2778753569","wikidata":"https://www.wikidata.org/wiki/Q1960395","display_name":"Span (engineering)","level":2,"score":0.6065806150436401},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5097381472587585},{"id":"https://openalex.org/C15708023","wikidata":"https://www.wikidata.org/wiki/Q80083","display_name":"Humanities","level":1,"score":0.4515135586261749},{"id":"https://openalex.org/C24351657","wikidata":"https://www.wikidata.org/wiki/Q1026962","display_name":"Digital humanities","level":2,"score":0.4316457211971283},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2360636293888092},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.21046742796897888},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.1995747685432434},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0834067165851593}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.8107808","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.8107808","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.8107808","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.8107808","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3016750667","https://openalex.org/W2134911674","https://openalex.org/W4235849696","https://openalex.org/W1480800433","https://openalex.org/W170186150","https://openalex.org/W2527879301","https://openalex.org/W2468691689","https://openalex.org/W4255837503"],"abstract_inverted_index":{"This":[0],"3-hour":[1],"workshop":[2],"will":[3,24],"introduce":[4],"span":[5,31,45],"categorization":[6,32],"as":[7],"a":[8,26,43],"method":[9],"for":[10,15],"the":[11,20,48],"machine-annotation":[12],"of":[13,29],"text":[14],"various":[16],"research":[17],"tasks":[18],"in":[19],"digital":[21],"humanities.":[22],"Participants":[23],"gain":[25],"conceptual":[27],"understanding":[28],"how":[30],"differs":[33],"from":[34],"entity":[35],"recognition":[36],"and":[37],"complete":[38],"practical":[39],"exercises":[40],"to":[41],"train":[42],"spaCy":[44],"categorizer":[46],"on":[47],"LitBank":[49],"dataset.":[50]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
