{"id":"https://openalex.org/W2282396980","doi":null,"title":"Learning Extractors from Unlabeled Text using Relevant Databases","display_name":"Learning Extractors from Unlabeled Text using Relevant Databases","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2282396980","mag":"2282396980"},"language":"en","primary_location":{"id":"pmh:oai:works.bepress.com:andrew_mccallum-1173","doi":null,"is_oa":true,"landing_page_url":"https://works.bepress.com/andrew_mccallum/99","pdf_url":"https://works.bepress.com/cgi/viewcontent.cgi?article=1173&context=andrew_mccallum","source":{"id":"https://openalex.org/S4306402057","display_name":"Scholarworks (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://works.bepress.com/cgi/viewcontent.cgi?article=1173&context=andrew_mccallum","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090835762","display_name":"Kedar Bellare","orcid":"https://orcid.org/0009-0004-6827-8719","observed_orcids":["https://orcid.org/0009-0004-6827-8719"]},"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":"Kedar Bellare","raw_affiliation_strings":["University of Massachusetts, Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107835063","display_name":"Andrew McCallum","orcid":"https://orcid.org/0000-0003-2843-6992","observed_orcids":["https://orcid.org/0000-0003-2843-6992"]},"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 McCallum","raw_affiliation_strings":["University of Massachusetts, Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst","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":1.9325,"has_fulltext":true,"cited_by_count":61,"citation_normalized_percentile":{"value":0.86178213,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.41920000314712524,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.41920000314712524,"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":0.21629999577999115,"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/T10028","display_name":"Topic Modeling","score":0.07580000162124634,"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/information-extraction","display_name":"information extraction","score":0.902999997138977},{"id":"https://openalex.org/keywords/unlabeled-text","display_name":"unlabeled text","score":0.6840000152587891},{"id":"https://openalex.org/keywords/partially-labeled-data","display_name":"partially labeled data","score":0.6290000081062317},{"id":"https://openalex.org/keywords/heuristics","display_name":"heuristics","score":0.7129999995231628},{"id":"https://openalex.org/keywords/research-papers","display_name":"research papers","score":0.47099998593330383},{"id":"https://openalex.org/keywords/training-data-labeling","display_name":"training data labeling","score":0.6039999723434448}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7988681793212891},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7550986409187317},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6321697235107422},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5332638025283813},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.5017621517181396},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49212950468063354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4856385290622711},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.45978620648384094},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4484538733959198},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41865745186805725},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3541097640991211},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33591142296791077},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3266229033470154},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:works.bepress.com:andrew_mccallum-1173","doi":null,"is_oa":true,"landing_page_url":"https://works.bepress.com/andrew_mccallum/99","pdf_url":"https://works.bepress.com/cgi/viewcontent.cgi?article=1173&context=andrew_mccallum","source":{"id":"https://openalex.org/S4306402057","display_name":"Scholarworks (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.132.8252","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.132.8252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.umass.edu/~mccallum/papers/bellare-iiweb07.pdf","raw_type":"text"},{"id":"mag:2282396980","doi":null,"is_oa":false,"landing_page_url":"https://ciir-publications.cs.umass.edu/pub/web/getpdf.php?id=772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:works.bepress.com:andrew_mccallum-1173","doi":null,"is_oa":true,"landing_page_url":"https://works.bepress.com/andrew_mccallum/99","pdf_url":"https://works.bepress.com/cgi/viewcontent.cgi?article=1173&context=andrew_mccallum","source":{"id":"https://openalex.org/S4306402057","display_name":"Scholarworks (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2282396980.pdf","grobid_xml":"https://content.openalex.org/works/W2282396980.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1534730506","https://openalex.org/W1568339100","https://openalex.org/W1954715867","https://openalex.org/W1980925709","https://openalex.org/W2048468185","https://openalex.org/W2121911355","https://openalex.org/W2124410446","https://openalex.org/W2125838338","https://openalex.org/W2139193890","https://openalex.org/W2145948275","https://openalex.org/W2147880316","https://openalex.org/W2155042384","https://openalex.org/W2158188757","https://openalex.org/W2162630660","https://openalex.org/W4253723135"],"related_works":["https://openalex.org/W7100238119","https://openalex.org/W276017482","https://openalex.org/W7100232260","https://openalex.org/W1975870392","https://openalex.org/W2388358427","https://openalex.org/W1498682480","https://openalex.org/W1981301418","https://openalex.org/W7100372462","https://openalex.org/W2127480284","https://openalex.org/W7095073138"],"abstract_inverted_index":{"Supervised":[0],"machine":[1],"learning":[2],"algorithms":[3],"for":[4,84,143],"information":[5],"extraction":[6,132],"generally":[7],"require":[8],"large":[9],"amounts":[10],"of":[11,92],"training":[12,19,85,144],"data.":[13,145],"In":[14,116],"many":[15],"cases":[16],"where":[17,55],"labeling":[18,72],"data":[20],"is":[21,97],"burdensome,":[22],"there":[23],"may,":[24],"however,":[25],"already":[26],"exist":[27],"an":[28],"incomplete":[29],"database":[30,40,142],"relevant":[31],"to":[32,44],"the":[33,50,61,73,107,114,141],"task":[34],"at":[35],"hand.":[36],"Records":[37],"from":[38,113],"this":[39],"can":[41],"be":[42,77],"used":[43],"label":[45],"text":[46,56,94],"strings":[47,57,74],"that":[48,96,137],"express":[49],"same":[51,62],"information.":[52],"For":[53],"tasks":[54],"do":[58],"not":[59],"follow":[60],"format":[63],"or":[64],"layout,":[65],"and":[66,121],"additionally":[67],"may":[68,76],"contain":[69],"extra":[70],"information,":[71],"completely":[75],"problematic.":[78],"This":[79],"paper":[80,123],"presents":[81],"a":[82,93,128,135],"method":[83],"extractors":[86],"which":[87],"fill":[88],"in":[89,131],"missing":[90],"labels":[91],"sequence":[95],"partially":[98],"labeled":[99,111],"using":[100],"simple":[101],"high-precision":[102],"heuristics.":[103],"Furthermore,":[104],"we":[105,126],"improve":[106],"algorithm":[108],"by":[109],"utilizing":[110],"fields":[112],"database.":[115],"experiments":[117],"with":[118],"BibTeX":[119],"records":[120],"research":[122],"citation":[124],"strings,":[125],"show":[127],"significant":[129],"improvement":[130],"accuracy":[133],"over":[134],"baseline":[136],"only":[138],"relies":[139],"on":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":5}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2016-06-24T00:00:00"}