{"id":"https://openalex.org/W2152749438","doi":"https://doi.org/10.1145/1401890.1401978","title":"Information extraction from Wikipedia","display_name":"Information extraction from Wikipedia","publication_year":2008,"publication_date":"2008-08-24","ids":{"openalex":"https://openalex.org/W2152749438","doi":"https://doi.org/10.1145/1401890.1401978","mag":"2152749438"},"language":"en","primary_location":{"id":"doi:10.1145/1401890.1401978","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5004882141","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0003-2139-8807"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fei Wu","raw_affiliation_strings":["University of Washington, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060819264","display_name":"Raphael Hoffmann","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raphael Hoffmann","raw_affiliation_strings":["University of Washington, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085011940","display_name":"Daniel S. Weld","orcid":"https://orcid.org/0000-0002-3255-0109"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel S. Weld","raw_affiliation_strings":["University of Washington, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004882141"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":26.3424,"has_fulltext":false,"cited_by_count":132,"citation_normalized_percentile":{"value":0.99589398,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"731","last_page":"739"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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":0.9991999864578247,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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/T12478","display_name":"Wikis in Education and Collaboration","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8277400732040405},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.6846854090690613},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6514085531234741},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.6355451941490173},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.6134966611862183},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5914375185966492},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.49971556663513184},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.4843538999557495},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.43133223056793213},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41041702032089233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3737414479255676},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.07651618123054504}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8277400732040405},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.6846854090690613},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6514085531234741},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.6355451941490173},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.6134966611862183},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5914375185966492},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.49971556663513184},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.4843538999557495},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.43133223056793213},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41041702032089233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3737414479255676},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.07651618123054504},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1401890.1401978","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W130452239","https://openalex.org/W157776793","https://openalex.org/W202303397","https://openalex.org/W1493490255","https://openalex.org/W1523949738","https://openalex.org/W1527110714","https://openalex.org/W1586197708","https://openalex.org/W1598266570","https://openalex.org/W1930023685","https://openalex.org/W1943691658","https://openalex.org/W1965605789","https://openalex.org/W1972644898","https://openalex.org/W1977970897","https://openalex.org/W2022166150","https://openalex.org/W2048679005","https://openalex.org/W2099685860","https://openalex.org/W2100805904","https://openalex.org/W2103931177","https://openalex.org/W2104009457","https://openalex.org/W2115758952","https://openalex.org/W2124067180","https://openalex.org/W2144108169","https://openalex.org/W2146304342","https://openalex.org/W2147880316","https://openalex.org/W2148540243","https://openalex.org/W2149820823","https://openalex.org/W2169463693","https://openalex.org/W4285719527","https://openalex.org/W6605290497","https://openalex.org/W6608351394","https://openalex.org/W6629638141","https://openalex.org/W6631446989"],"related_works":["https://openalex.org/W842810586","https://openalex.org/W4319940250","https://openalex.org/W2352298027","https://openalex.org/W2092919065","https://openalex.org/W3138801416","https://openalex.org/W4236762297","https://openalex.org/W2444550338","https://openalex.org/W2369351710","https://openalex.org/W2594363579","https://openalex.org/W2169232658"],"abstract_inverted_index":{"Not":[0],"only":[1],"is":[2],"Wikipedia":[3,34],"a":[4,48,91,125],"comprehensive":[5],"source":[6],"of":[7,14,43,51,60,80,127],"quality":[8],"information,":[9],"it":[10],"has":[11],"several":[12],"kinds":[13],"internal":[15],"structure":[16],"(e.g.,":[17],"relational":[18],"summaries":[19],"known":[20],"as":[21],"infoboxes),":[22],"which":[23],"enable":[24],"self-supervised":[25],"information":[26],"extraction.":[27],"While":[28],"previous":[29],"efforts":[30],"at":[31],"extraction":[32],"from":[33,76,105],"achieve":[35],"high":[36],"precision":[37],"and":[38,57,99,114],"recall":[39,75,123],"on":[40],"well-populated":[41],"classes":[42],"articles,":[44],"they":[45],"fail":[46],"in":[47,118],"larger":[49],"number":[50],"cases,":[52],"largely":[53],"because":[54],"incomplete":[55],"articles":[56],"infrequent":[58],"use":[59],"infoboxes":[61],"lead":[62],"to":[63,129],"insufficient":[64],"training":[65,97],"data.":[66],"This":[67],"paper":[68],"presents":[69],"three":[70],"novel":[71],"techniques":[72,121],"for":[73,94],"increasing":[74,134],"Wikipedia's":[77],"long":[78],"tail":[79],"sparse":[81],"classes:":[82],"(1)":[83],"shrinkage":[84],"over":[85],"an":[86],"automatically-learned":[87],"subsumption":[88],"taxonomy,":[89],"(2)":[90],"retraining":[92],"technique":[93],"improving":[95],"the":[96,106],"data,":[98],"(3)":[100],"supplementing":[101],"results":[102],"by":[103,124],"extracting":[104],"broader":[107],"Web.":[108],"Our":[109],"experiments":[110],"compare":[111],"design":[112],"variations":[113],"show":[115],"that,":[116],"used":[117],"concert,":[119],"these":[120],"increase":[122],"factor":[126],"1.76":[128],"8.71":[130],"while":[131],"maintaining":[132],"or":[133],"precision.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":16},{"year":2012,"cited_by_count":14}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}