{"id":"https://openalex.org/W2080190461","doi":"https://doi.org/10.1109/icdew.2014.6818305","title":"Scholarly big data information extraction and integration in the CiteSeer&lt;sup&gt;&amp;#x03C7;&lt;/sup&gt; digital library","display_name":"Scholarly big data information extraction and integration in the CiteSeer&lt;sup&gt;&amp;#x03C7;&lt;/sup&gt; digital library","publication_year":2014,"publication_date":"2014-03-01","ids":{"openalex":"https://openalex.org/W2080190461","doi":"https://doi.org/10.1109/icdew.2014.6818305","mag":"2080190461"},"language":"en","primary_location":{"id":"doi:10.1109/icdew.2014.6818305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdew.2014.6818305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 30th International Conference on Data Engineering Workshops","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"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":["Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","Information Sciences and Technology, Pennsylvania State University, University Park, PA 16802, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Information Sciences and Technology, Pennsylvania State University, University Park, PA 16802, 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":["Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","Information Sciences and Technology, Pennsylvania State University, University Park, PA 16802, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Information Sciences and Technology, Pennsylvania State University, University Park, PA 16802, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112500027","display_name":"Sagnik Ray Choudhury","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":false,"raw_author_name":"Sagnik Ray Choudhury","raw_affiliation_strings":["Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","Information Sciences and Technology, Pennsylvania State University, University Park, PA 16802, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Information Sciences and Technology, Pennsylvania State University, University Park, PA 16802, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054253075","display_name":"Madian Khabsa","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":false,"raw_author_name":"Madian Khabsa","raw_affiliation_strings":["Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA","[Computer Science and Engineering, Pennsylvania State University, University Park, PA 16802, USA]"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"[Computer Science and Engineering, Pennsylvania State University, University Park, PA 16802, 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":["Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA","[Computer Science and Engineering, Pennsylvania State University, University Park, PA 16802, USA]"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"[Computer Science and Engineering, Pennsylvania State University, University Park, PA 16802, USA]","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5108439761"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":4.464,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.94375224,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"68","last_page":"73"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7746732831001282},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.657593846321106},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.5800482034683228},{"id":"https://openalex.org/keywords/citation","display_name":"Citation","score":0.5570053458213806},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5259454846382141},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5133939981460571},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5113438963890076},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5095084309577942},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.4948102831840515},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4773968756198883},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4605601727962494},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3257107138633728},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2509656846523285}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7746732831001282},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.657593846321106},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.5800482034683228},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.5570053458213806},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5259454846382141},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5133939981460571},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5113438963890076},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5095084309577942},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.4948102831840515},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4773968756198883},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4605601727962494},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3257107138633728},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2509656846523285},{"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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdew.2014.6818305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdew.2014.6818305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 30th International Conference on Data Engineering Workshops","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.5299999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320315666","display_name":"Medicines Company","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1559499673","https://openalex.org/W1968774519","https://openalex.org/W1996457856","https://openalex.org/W2028657008","https://openalex.org/W2042014073","https://openalex.org/W2042641525","https://openalex.org/W2057954853","https://openalex.org/W2080099271","https://openalex.org/W2083089853","https://openalex.org/W2091344457","https://openalex.org/W2098564132","https://openalex.org/W2129647599","https://openalex.org/W2132083030","https://openalex.org/W2140479099","https://openalex.org/W2173213060","https://openalex.org/W2253675773","https://openalex.org/W2727840914","https://openalex.org/W4253723135","https://openalex.org/W6633305578","https://openalex.org/W6691667650","https://openalex.org/W6892301120"],"related_works":["https://openalex.org/W2381351160","https://openalex.org/W2963735687","https://openalex.org/W1556178152","https://openalex.org/W4300081969","https://openalex.org/W2523290178","https://openalex.org/W3169992079","https://openalex.org/W1557235427","https://openalex.org/W2398590682","https://openalex.org/W2778567813","https://openalex.org/W2583061389"],"abstract_inverted_index":{"CiteSeer<sup>&#x03C7;</sup>":[0,56],"is":[1,34,94,104],"a":[2,29,72,128],"digital":[3],"library":[4],"that":[5,92,176],"contains":[6],"approximately":[7],"3.5":[8],"million":[9,18],"scholarly":[10,112],"documents":[11,26,113],"and":[12,16,50,69,97,114,146,164,180,185,191,194,198,205],"receives":[13],"between":[14],"2":[15],"4":[17],"requests":[19],"per":[20],"day.":[21],"In":[22,123],"addition":[23],"to":[24,37,110,141,202],"making":[25],"available":[27,201],"via":[28],"public":[30,109],"Website,":[31],"the":[32,60,81,85,88,90,98,108,161],"data":[33,121,144,156,168,197],"also":[35],"used":[36,105],"facilitate":[38],"research":[39,204],"in":[40,55,101,149],"areas":[41],"like":[42],"citation":[43,186],"analysis,":[44,47],"co-author":[45],"network":[46],"scalability":[48],"evaluation":[49],"information":[51,142,181],"extraction.":[52],"The":[53],"papers":[54],"are":[57,118],"gathered":[58],"from":[59,157],"Web":[61],"by":[62,107],"means":[63],"of":[64,74,80,87,132,171],"continuous":[65],"automatic":[66,75,173,178],"focused":[67],"crawling":[68],"go":[70],"through":[71],"series":[73],"processing":[76],"steps":[77],"as":[78,169],"part":[79,170],"ingestion":[82,174],"process.":[83],"Given":[84],"size":[86],"collection,":[89],"fact":[91],"it":[93,103,139],"constantly":[95],"expanding,":[96],"multiple":[99,158],"ways":[100],"which":[102],"both":[106],"access":[111],"for":[115],"research,":[116],"there":[117],"several":[119],"big":[120],"challenges.":[122],"this":[124],"paper,":[125],"we":[126,134],"provide":[127],"case":[129],"study":[130],"description":[131],"how":[133,153],"address":[135],"these":[136],"challenges":[137],"when":[138],"comes":[140],"extraction,":[143],"integration":[145],"entity":[147,189],"linking":[148,190],"CiteSeer<sup>&#x03C7;</sup>.":[150],"We":[151],"describe":[152],"we:":[154],"aggregate":[155],"sources":[159],"on":[160],"Web;":[162],"store":[163],"manage":[165],"data;":[166],"process":[167],"an":[172],"pipeline":[175],"includes":[177],"metadata":[179],"extraction;":[182],"perform":[183,188],"document":[184],"clustering;":[187],"name":[192],"disambiguation;":[193],"make":[195],"our":[196],"source":[199],"code":[200],"enable":[203],"collaboration.":[206]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
