{"id":"https://openalex.org/W2068431743","doi":"https://doi.org/10.1145/1298406.1298425","title":"Strategies for lifelong knowledge extraction from the web","display_name":"Strategies for lifelong knowledge extraction from the web","publication_year":2007,"publication_date":"2007-10-28","ids":{"openalex":"https://openalex.org/W2068431743","doi":"https://doi.org/10.1145/1298406.1298425","mag":"2068431743"},"language":"en","primary_location":{"id":"doi:10.1145/1298406.1298425","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1298406.1298425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th international conference on Knowledge capture","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/A5067892737","display_name":"Michele Banko","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":true,"raw_author_name":"Michele Banko","raw_affiliation_strings":["University of Washington, Seattle, WA","University Of Washington (Seattle, WA)"],"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University Of Washington (Seattle, WA)","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110184338","display_name":"Oren Etzioni","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":"Oren Etzioni","raw_affiliation_strings":["University of Washington, Seattle, WA","University Of Washington (Seattle, WA)"],"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University Of Washington (Seattle, WA)","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5067892737"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":11.5911,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":{"value":0.98354608,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"95","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9979000091552734,"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":0.7966712117195129},{"id":"https://openalex.org/keywords/lifelong-learning","display_name":"Lifelong learning","score":0.6077390909194946},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5821080803871155},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.52070552110672},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.5162920355796814},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.5099784135818481},{"id":"https://openalex.org/keywords/sophistication","display_name":"Sophistication","score":0.5076781511306763},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47157803177833557},{"id":"https://openalex.org/keywords/knowledge-acquisition","display_name":"Knowledge acquisition","score":0.4291613698005676},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3730832040309906},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3538628816604614}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7966712117195129},{"id":"https://openalex.org/C108771440","wikidata":"https://www.wikidata.org/wiki/Q368475","display_name":"Lifelong learning","level":2,"score":0.6077390909194946},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5821080803871155},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.52070552110672},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.5162920355796814},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.5099784135818481},{"id":"https://openalex.org/C168725872","wikidata":"https://www.wikidata.org/wiki/Q991663","display_name":"Sophistication","level":2,"score":0.5076781511306763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47157803177833557},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.4291613698005676},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3730832040309906},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3538628816604614},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1298406.1298425","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1298406.1298425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th international conference on Knowledge capture","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.108.8982","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.108.8982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://turing.cs.washington.edu/papers/kcapfp05-banko.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310094","display_name":"University of Washington","ror":"https://ror.org/00cvxb145"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W146175359","https://openalex.org/W157725869","https://openalex.org/W1493490255","https://openalex.org/W1584431645","https://openalex.org/W1991564165","https://openalex.org/W2003154243","https://openalex.org/W2003698958","https://openalex.org/W2012179495","https://openalex.org/W2022166150","https://openalex.org/W2107325952","https://openalex.org/W2126204609","https://openalex.org/W2127218421","https://openalex.org/W2148540243","https://openalex.org/W2913629715","https://openalex.org/W2914048451","https://openalex.org/W6606033109","https://openalex.org/W6629638141","https://openalex.org/W6759229479","https://openalex.org/W6759284170"],"related_works":["https://openalex.org/W2357854711","https://openalex.org/W1582777578","https://openalex.org/W4243448361","https://openalex.org/W2125479495","https://openalex.org/W2051700896","https://openalex.org/W1552255772","https://openalex.org/W1559202216","https://openalex.org/W2111524952","https://openalex.org/W2054759342","https://openalex.org/W2143742390"],"abstract_inverted_index":{"The":[0],"increasing":[1,61],"availability":[2],"of":[3,16,22,31,63,69,104,122,163,173,180,208],"electronic":[4],"text":[5],"has":[6,43],"made":[7],"it":[8],"possible":[9],"to":[10,91,117,144,159],"acquire":[11],"information":[12,189],"using":[13],"a":[14,70,74,99,133,152,170,177,206],"variety":[15],"techniques":[17],"that":[18,114,168,193],"leverage":[19],"the":[20,29,67,108,115,120],"expertise":[21],"both":[23],"humans":[24],"and":[25,80,107,128,166,200],"machines.":[26],"In":[27],"particular,":[28],"field":[30],"Information":[32],"Extraction":[33],"(IE),":[34],"in":[35,137,187],"which":[36,138],"knowledge":[37,48,103,123,141,204],"is":[38,142,158],"extracted":[39],"automatically":[40,160],"from":[41,73,176],"text,":[42],"shown":[44],"promise":[45],"for":[46],"large-scale":[47],"acquisition.":[49],"While":[50],"IE":[51,88,97],"systems":[52],"can":[53,195],"uncover":[54],"assertions":[55,94],"about":[56],"individual":[57,92],"entities":[58],"with":[59,205],"an":[60],"level":[62],"sophistication,alltext":[64],"understanding":[65],"--":[66,77],"formation":[68],"coherent":[71,102],"theory":[72,100],"textual":[75],"corpus":[76],"involves":[78],"representation":[79],"learning":[81,135,154],"abilities":[82],"not":[83],"currently":[84],"achievable":[85],"by":[86,96],"today's":[87],"systems.":[89],"Compared":[90],"relational":[93],"outputted":[95],"systems,":[98],"includes":[101],"abstract":[105],"concepts":[106,199],"relationships":[109],"among":[110],"them.":[111],"We":[112],"believe":[113],"ability":[116],"fully":[118],"discover":[119,197],"richness":[121],"present":[124],"within":[125],"large,":[126],"unstructured":[127],"heterogeneous":[129],"corpora":[130],"will":[131],"require":[132],"lifelong":[134,153],"process":[136],"earlier":[139],"learned":[140],"used":[143],"guide":[145],"subsequent":[146],"learning.":[147],"This":[148],"paper":[149],"introduces":[150],"Alice,":[151],"agent":[155],"whose":[156],"goal":[157],"discovera":[161],"collection":[162],"concepts,":[164],"facts":[165],"generalizations":[167],"describe":[169],"particular":[171],"topic":[172],"interest":[174],"directly":[175],"large":[178],"volume":[179],"Web":[181],"text.":[182],"Building":[183],"upon":[184],"recent":[185],"advances":[186],"unsupervised":[188],"extraction,":[190],"we":[191],"demonstrate":[192],"Alice":[194],"iteratively":[196],"new":[198],"compose":[201],"general":[202],"domain":[203],"precision":[207],"78%.":[209]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}