{"id":"https://openalex.org/W2413378117","doi":"https://doi.org/10.1145/2910896.2925430","title":"Information Extraction for Scholarly Digital Libraries","display_name":"Information Extraction for Scholarly Digital Libraries","publication_year":2016,"publication_date":"2016-06-10","ids":{"openalex":"https://openalex.org/W2413378117","doi":"https://doi.org/10.1145/2910896.2925430","mag":"2413378117"},"language":"en","primary_location":{"id":"doi:10.1145/2910896.2925430","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2910896.2925430","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2925430&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM/IEEE-CS on Joint Conference on Digital Libraries","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2925430&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108439761","display_name":"Kyle Williams","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kyle Williams","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075242841","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0003-0173-4463"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101973484","display_name":"Zhaohui Wu","orcid":"https://orcid.org/0000-0002-4319-3645"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaohui Wu","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108439761"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.06004177,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"287","last_page":"288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9987000226974487,"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/T13976","display_name":"Web visibility and informetrics","score":0.9976999759674072,"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/T11719","display_name":"Data Quality and Management","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.8407580852508545},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8320108652114868},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.7920341491699219},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6882842779159546},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6516910791397095},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5815936326980591},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5571324229240417},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.549960732460022},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5253466963768005},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.4674806296825409},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.41702964901924133},{"id":"https://openalex.org/keywords/scholarly-communication","display_name":"Scholarly communication","score":0.4158467650413513},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.185818612575531},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17125818133354187},{"id":"https://openalex.org/keywords/publishing","display_name":"Publishing","score":0.09232008457183838}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8407580852508545},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8320108652114868},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.7920341491699219},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6882842779159546},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6516910791397095},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5815936326980591},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5571324229240417},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.549960732460022},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5253466963768005},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.4674806296825409},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.41702964901924133},{"id":"https://openalex.org/C2777462167","wikidata":"https://www.wikidata.org/wiki/Q7432048","display_name":"Scholarly communication","level":3,"score":0.4158467650413513},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.185818612575531},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17125818133354187},{"id":"https://openalex.org/C151719136","wikidata":"https://www.wikidata.org/wiki/Q3972943","display_name":"Publishing","level":2,"score":0.09232008457183838},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2910896.2925430","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2910896.2925430","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2925430&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM/IEEE-CS on Joint Conference on Digital Libraries","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2910896.2925430","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2910896.2925430","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2925430&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM/IEEE-CS on Joint Conference on Digital Libraries","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2413378117.pdf","grobid_xml":"https://content.openalex.org/works/W2413378117.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W1991869139","https://openalex.org/W1992464666","https://openalex.org/W2084745915","https://openalex.org/W2098564132","https://openalex.org/W2156838832","https://openalex.org/W3182392724"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2010935248"],"abstract_inverted_index":{"Scholarly":[0],"documents":[1],"contain":[2],"many":[3],"data":[4],"entities,":[5],"such":[6],"as":[7],"titles,":[8],"authors,":[9],"affiliations,":[10],"figures,":[11],"and":[12,27,34,39,58,118,124,128],"tables.":[13],"These":[14],"entities":[15,53],"can":[16,61],"be":[17,62],"used":[18],"to":[19],"enhance":[20],"digital":[21,77,87],"library":[22],"services":[23,33],"through":[24],"enhanced":[25],"metadata":[26],"enable":[28],"the":[29,69,85,103],"development":[30],"of":[31,47,72,130],"new":[32],"tools":[35,117],"for":[36,75,102,105,112],"interacting":[37],"with":[38],"exploring":[40],"scholarly":[41,48,76],"data.":[42],"However,":[43],"in":[44,54,83],"a":[45,55],"world":[46],"big":[49],"data,":[50],"extracting":[51],"these":[52],"scalable,":[56],"efficient":[57],"accurate":[59],"manner":[60],"challenging.":[63],"In":[64],"this":[65],"tutorial,":[66],"we":[67,100],"introduce":[68],"broad":[70],"field":[71],"information":[73,92,107,114],"extraction":[74,93],"libraries.":[78],"Drawing":[79],"on":[80,94],"our":[81],"experience":[82],"running":[84],"CiteSeerX":[86],"library,":[88],"which":[89],"has":[90],"performed":[91],"over":[95],"7":[96],"million":[97],"academic":[98],"documents,":[99],"argue":[101],"need":[104],"automatic":[106],"extraction,":[108,115],"describe":[109,125],"different":[110],"approaches":[111],"performing":[113],"present":[116],"datasets":[119],"that":[120],"are":[121],"readily":[122],"available,":[123],"best":[126],"practices":[127],"areas":[129],"research":[131],"interest.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
