{"id":"https://openalex.org/W2805334254","doi":"https://doi.org/10.1145/3197026.3203875","title":"Providing Pin-point Page-level Precision to 1 Trillion Tokens of Text for Workset Creation","display_name":"Providing Pin-point Page-level Precision to 1 Trillion Tokens of Text for Workset Creation","publication_year":2018,"publication_date":"2018-05-23","ids":{"openalex":"https://openalex.org/W2805334254","doi":"https://doi.org/10.1145/3197026.3203875","mag":"2805334254"},"language":"en","primary_location":{"id":"doi:10.1145/3197026.3203875","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3197026.3203875","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/IEEE on Joint Conference on Digital Libraries","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/10289/11929","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017432361","display_name":"David Bainbridge","orcid":"https://orcid.org/0000-0002-0603-5728"},"institutions":[{"id":"https://openalex.org/I52179390","display_name":"University of Waikato","ror":"https://ror.org/013fsnh78","country_code":"NZ","type":"education","lineage":["https://openalex.org/I52179390"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"David Bainbridge","raw_affiliation_strings":["University of Waikato, Hamilton, New Zealand"],"affiliations":[{"raw_affiliation_string":"University of Waikato, Hamilton, New Zealand","institution_ids":["https://openalex.org/I52179390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016957740","display_name":"J. Stephen Downie","orcid":"https://orcid.org/0000-0001-9784-5090"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Stephen Downie","raw_affiliation_strings":["University of Illinois at Urbana Champaign, Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048070110","display_name":"Boris Capitanu","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Capitanu","raw_affiliation_strings":["University of Illinois at Urbana Champaign, Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017432361"],"corresponding_institution_ids":["https://openalex.org/I52179390"],"apc_list":null,"apc_paid":null,"fwci":0.1629,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56927346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"407","last_page":"408"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9986000061035156,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8376179933547974},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.6466443538665771},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5497373938560486},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.42115747928619385},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3859289288520813}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8376179933547974},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.6466443538665771},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5497373938560486},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.42115747928619385},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3859289288520813},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3197026.3203875","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3197026.3203875","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/IEEE on Joint Conference on Digital Libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:researchcommons.waikato.ac.nz:10289/11929","is_oa":true,"landing_page_url":"https://hdl.handle.net/10289/11929","pdf_url":"https://hdl.handle.net/10289/11929","source":{"id":"https://openalex.org/S4306400944","display_name":"Research Commons (University of Waikato)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I52179390","host_organization_name":"University of Waikato","host_organization_lineage":["https://openalex.org/I52179390"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"JCDL 2018","raw_type":"Conference Contribution"}],"best_oa_location":{"id":"pmh:oai:researchcommons.waikato.ac.nz:10289/11929","is_oa":true,"landing_page_url":"https://hdl.handle.net/10289/11929","pdf_url":"https://hdl.handle.net/10289/11929","source":{"id":"https://openalex.org/S4306400944","display_name":"Research Commons (University of Waikato)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I52179390","host_organization_name":"University of Waikato","host_organization_lineage":["https://openalex.org/I52179390"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"JCDL 2018","raw_type":"Conference Contribution"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2805334254.pdf"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2703465466","https://openalex.org/W2949259776"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W1488511360","https://openalex.org/W1781894645","https://openalex.org/W2894902932","https://openalex.org/W569715723","https://openalex.org/W188332989","https://openalex.org/W2982387199","https://openalex.org/W2000745862","https://openalex.org/W2120930843","https://openalex.org/W42013907"],"abstract_inverted_index":{"We":[0,41],"report":[1],"on":[2],"the":[3,24,28,47],"work":[4],"undertaken":[5],"developing":[6],"a":[7],"web":[8,48],"environment":[9,49],"that":[10],"allows":[11],"users":[12],"to":[13,23,34],"search":[14],"over":[15],"1":[16],"trillion":[17],"tokens":[18],"of":[19,27,46],"text":[20],"--":[21,26],"down":[22],"page-level":[25],"HathiTrust":[29],"Part-of-Speech":[30],"Extracted":[31],"Features":[32],"Dataset":[33],"help":[35],"produce":[36],"worksets":[37],"for":[38],"scholarly":[39],"analysis.":[40],"present":[42],"an":[43],"extended":[44],"example":[45],"in":[50],"use,":[51],"along":[52],"with":[53],"details":[54],"about":[55],"its":[56],"implementation.":[57]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
