{"id":"https://openalex.org/W2012910912","doi":"https://doi.org/10.1145/2124295.2124328","title":"Selecting actions for resource-bounded information extraction using reinforcement learning","display_name":"Selecting actions for resource-bounded information extraction using reinforcement learning","publication_year":2012,"publication_date":"2012-02-08","ids":{"openalex":"https://openalex.org/W2012910912","doi":"https://doi.org/10.1145/2124295.2124328","mag":"2012910912"},"language":"en","primary_location":{"id":"doi:10.1145/2124295.2124328","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2124295.2124328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fifth ACM international conference on Web search and data mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://works.bepress.com/andrew_mccallum/68/download/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058039662","display_name":"Pallika Kanani","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pallika H. Kanani","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA","University Of Massachusetts Amherst, Amherst, MA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University Of Massachusetts Amherst, Amherst, MA, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103424470","display_name":"Andrew Kachites McCallum","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew K. McCallum","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA","University Of Massachusetts Amherst, Amherst, MA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University Of Massachusetts Amherst, Amherst, MA, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":2.176,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.88176505,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"253","last_page":"262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9975000023841858,"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":0.9975000023841858,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9965000152587891,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9958000183105469,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8582034111022949},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.802147388458252},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7023937106132507},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5969217419624329},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5948799252510071},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5569964051246643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5448921918869019},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4999260902404785},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4694706201553345},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07693156599998474}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8582034111022949},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.802147388458252},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7023937106132507},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5969217419624329},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5948799252510071},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5569964051246643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5448921918869019},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4999260902404785},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4694706201553345},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07693156599998474},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2124295.2124328","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2124295.2124328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fifth ACM international conference on Web search and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:works.bepress.com:andrew_mccallum-1111","is_oa":true,"landing_page_url":"https://works.bepress.com/andrew_mccallum/68","pdf_url":"https://works.bepress.com/andrew_mccallum/68/download/","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Andrew McCallum","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:works.bepress.com:andrew_mccallum-1111","is_oa":true,"landing_page_url":"https://works.bepress.com/andrew_mccallum/68","pdf_url":"https://works.bepress.com/andrew_mccallum/68/download/","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Andrew McCallum","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.6100000143051147}],"awards":[{"id":"https://openalex.org/G7704502625","display_name":"ITR:     Unified Graphical Models of Information Extraction and Data Mining with Application to Social Network Analysis","funder_award_id":"0326249","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"},{"id":"https://openalex.org/F4320311089","display_name":"National Security Agency","ror":"https://ror.org/0047bvr32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2012910912.pdf","grobid_xml":"https://content.openalex.org/works/W2012910912.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W185575639","https://openalex.org/W204009595","https://openalex.org/W225641137","https://openalex.org/W1485477363","https://openalex.org/W1515851193","https://openalex.org/W1542882058","https://openalex.org/W2023543851","https://openalex.org/W2038576084","https://openalex.org/W2045410140","https://openalex.org/W2110523400","https://openalex.org/W2112683085","https://openalex.org/W2115461474","https://openalex.org/W2121863487","https://openalex.org/W2122410182","https://openalex.org/W2137507956","https://openalex.org/W2152749438","https://openalex.org/W2169538431","https://openalex.org/W2284030692","https://openalex.org/W2964075712","https://openalex.org/W6607527603"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Given":[0],"a":[1,22,43,90,120],"database":[2,16],"with":[3],"missing":[4],"or":[5],"uncertain":[6],"content,":[7],"our":[8,107],"goal":[9],"is":[10],"to":[11,30,55,70,81],"correct":[12],"and":[13,29,51,78,100,109],"fill":[14],"the":[15,27,38,57,72,104,112,133],"by":[17,136],"extracting":[18],"specific":[19],"information":[20,39,94],"from":[21],"large":[23],"corpus":[24],"such":[25,95],"as":[26,42,96],"Web,":[28],"do":[31],"so":[32],"under":[33,119],"resource":[34],"limitations.":[35],"We":[36,64,88],"formulate":[37],"gathering":[40],"task":[41,117],"series":[44],"of":[45,132,140],"choices":[46],"among":[47],"alternative,":[48],"resource-consuming":[49],"actions":[50],"use":[52,65],"reinforcement":[53],"learning":[54],"select":[56],"best":[58],"action":[59,122],"at":[60,106],"each":[61],"time":[62],"step.":[63],"temporal":[66],"difference":[67],"q-learning":[68],"method":[69],"train":[71],"function":[73],"that":[74,92,111,127],"selects":[75],"these":[76],"actions,":[77],"compare":[79],"it":[80],"an":[82],"online,":[83],"error-driven":[84],"algorithm":[85],"called":[86],"SampleRank.":[87],"present":[89],"system":[91],"finds":[93],"email,":[97],"job":[98],"title":[99],"department":[101],"affiliation":[102],"for":[103],"faculty":[105],"university,":[108],"show":[110,126],"learning-based":[113],"approach":[114],"accomplishes":[115],"this":[116],"efficiently":[118],"limited":[121],"budget.":[123],"Our":[124],"evaluations":[125],"we":[128],"can":[129],"obtain":[130],"92.4%":[131],"final":[134],"F1,":[135],"only":[137],"using":[138],"14.3%":[139],"all":[141],"possible":[142],"actions.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-08-27T14:10:00.468798","created_date":"2025-10-10T00:00:00"}