{"id":"https://openalex.org/W2494261950","doi":"https://doi.org/10.1145/2928294.2928306","title":"CiteSeerX data","display_name":"CiteSeerX data","publication_year":2016,"publication_date":"2016-06-02","ids":{"openalex":"https://openalex.org/W2494261950","doi":"https://doi.org/10.1145/2928294.2928306","mag":"2494261950"},"language":"en","primary_location":{"id":"doi:10.1145/2928294.2928306","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2928294.2928306","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2928306&type=pdf","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on Semantic Big Data","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=2928306&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075242841","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0003-0173-4463"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jian Wu","raw_affiliation_strings":["Information Sciences and Technology"],"affiliations":[{"raw_affiliation_string":"Information Sciences and Technology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053537544","display_name":"Chen Liang","orcid":"https://orcid.org/0000-0002-0124-4133"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Liang","raw_affiliation_strings":["Information Sciences and Technology"],"affiliations":[{"raw_affiliation_string":"Information Sciences and Technology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087529969","display_name":"Huaiyu Yang","orcid":"https://orcid.org/0000-0003-2358-1840"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huaiyu Yang","raw_affiliation_strings":["Vanderbilt University, Nashville, TN"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University, Nashville, TN","institution_ids":["https://openalex.org/I200719446"]}]},{"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":["Information Sciences and Technology and Pennsylvania State University, PA"],"affiliations":[{"raw_affiliation_string":"Information Sciences and Technology and Pennsylvania State University, PA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5075242841"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2086,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.90821459,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9287999868392944,"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/T10028","display_name":"Topic Modeling","score":0.9287999868392944,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5741459727287292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5741459727287292}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2928294.2928306","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2928294.2928306","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2928306&type=pdf","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on Semantic Big Data","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2928294.2928306","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2928294.2928306","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2928306&type=pdf","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on Semantic Big Data","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"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/W2494261950.pdf","grobid_xml":"https://content.openalex.org/works/W2494261950.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1559499673","https://openalex.org/W1603719052","https://openalex.org/W1932742904","https://openalex.org/W1991869139","https://openalex.org/W1999254925","https://openalex.org/W2005653608","https://openalex.org/W2023930240","https://openalex.org/W2034604471","https://openalex.org/W2042641525","https://openalex.org/W2053299703","https://openalex.org/W2057954853","https://openalex.org/W2060186854","https://openalex.org/W2083089853","https://openalex.org/W2098564132","https://openalex.org/W2101680936","https://openalex.org/W2109215439","https://openalex.org/W2112497803","https://openalex.org/W2140479099","https://openalex.org/W2147107544","https://openalex.org/W2149155847","https://openalex.org/W2151048449","https://openalex.org/W2168065722","https://openalex.org/W2172271464","https://openalex.org/W2192866431","https://openalex.org/W2250869925","https://openalex.org/W2295508865","https://openalex.org/W2396548122","https://openalex.org/W2469279958","https://openalex.org/W2522338500","https://openalex.org/W2562691023","https://openalex.org/W2602331152","https://openalex.org/W3105689620","https://openalex.org/W6653447587","https://openalex.org/W6691332274"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Scholarly":[0],"big":[1,37],"data":[2,38,56,63],"is,":[3],"for":[4],"many,":[5],"an":[6,32],"important":[7,103,107],"instance":[8],"of":[9,26,34,43,46,76],"Big":[10],"Data.":[11],"Digital":[12],"library":[13],"search":[14],"engines":[15],"have":[16],"been":[17],"built":[18],"to":[19],"acquire,":[20],"extract,":[21],"and":[22,48,65,89],"ingest":[23],"large":[24],"volumes":[25],"scholarly":[27,36,77,110],"papers.":[28,111],"This":[29],"paper":[30],"provides":[31],"overview":[33],"the":[35,44,55,97],"released":[39],"by":[40],"CiteSeerX,":[41],"as":[42,53],"end":[45],"2015,":[47],"discusses":[49],"various":[50],"aspects":[51],"such":[52],"how":[54],"is":[57],"acquired,":[58],"its":[59],"size,":[60],"general":[61,84],"quality,":[62],"management,":[64],"accessibility.":[66],"Preliminary":[67],"results":[68],"on":[69],"extracting":[70,106],"semantic":[71],"entities":[72],"from":[73,109],"body":[74],"text":[75],"papers":[78],"with":[79],"Wikifier":[80],"show":[81],"biases":[82],"towards":[83],"terms":[85],"appearing":[86],"in":[87,105],"Wikipedia":[88],"against":[90],"domain":[91],"specific":[92],"terms.":[93],"We":[94],"argue":[95],"that":[96],"latter":[98],"will":[99],"play":[100],"a":[101],"more":[102],"role":[104],"facts":[108]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2016-08-23T00:00:00"}