{"id":"https://openalex.org/W2252074436","doi":"https://doi.org/10.18653/v1/d13-1042","title":"Joint Bootstrapping of Corpus Annotations and Entity Types","display_name":"Joint Bootstrapping of Corpus Annotations and Entity Types","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2252074436","doi":"https://doi.org/10.18653/v1/d13-1042","mag":"2252074436"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d13-1042","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d13-1042","pdf_url":"https://aclanthology.org/D13-1042.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/D13-1042.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063044201","display_name":"Hrushikesh Mohapatra","orcid":null},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]},{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Hrushikesh Mohapatra","raw_affiliation_strings":["IIT Bombay","Walmart (United States), Bentonville, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Bombay","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"Walmart (United States), Bentonville, United States","institution_ids":["https://openalex.org/I1330693074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102816915","display_name":"Siddhanth Jain","orcid":"https://orcid.org/0000-0003-4746-1552"},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]},{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Siddhanth Jain","raw_affiliation_strings":["IIT Bombay","Walmart (United States), Bentonville, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Bombay","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"Walmart (United States), Bentonville, United States","institution_ids":["https://openalex.org/I1330693074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101457009","display_name":"Soumen Chakrabarti","orcid":"https://orcid.org/0000-0002-9419-7486"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Soumen Chakrabarti","raw_affiliation_strings":["IIT Bombay","Indian Institute of Technology Bombay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Bombay","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"Indian Institute of Technology Bombay","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9883,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83914978,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"436","last_page":"446"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9915000200271606,"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":0.9040275812149048},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6631603837013245},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5166023969650269},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.46698635816574097},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4661701023578644},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.46347200870513916},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4618825614452362},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4563989043235779},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4445628821849823},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.42805689573287964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2932754158973694},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.2610777020454407}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9040275812149048},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6631603837013245},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5166023969650269},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.46698635816574097},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4661701023578644},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.46347200870513916},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4618825614452362},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4563989043235779},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4445628821849823},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.42805689573287964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2932754158973694},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.2610777020454407},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/d13-1042","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d13-1042","pdf_url":"https://aclanthology.org/D13-1042.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.592.8535","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.592.8535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/D/D13/D13-1042.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/d13-1042","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d13-1042","pdf_url":"https://aclanthology.org/D13-1042.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2252074436.pdf","grobid_xml":"https://content.openalex.org/works/W2252074436.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W11298561","https://openalex.org/W86887328","https://openalex.org/W1565763308","https://openalex.org/W1956559956","https://openalex.org/W2008036300","https://openalex.org/W2022166150","https://openalex.org/W2029249040","https://openalex.org/W2085337304","https://openalex.org/W2093903870","https://openalex.org/W2096765155","https://openalex.org/W2098700435","https://openalex.org/W2100341149","https://openalex.org/W2115352105","https://openalex.org/W2131357087","https://openalex.org/W2144886574","https://openalex.org/W2146772539","https://openalex.org/W2149746394","https://openalex.org/W2151048449","https://openalex.org/W2153848201","https://openalex.org/W2164918853","https://openalex.org/W2168859760"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Web":[0,12,148],"search":[1],"can":[2],"be":[3,27],"enhanced":[4],"in":[5,11,85,105,139,144],"powerful":[6],"ways":[7],"if":[8],"token":[9],"spans":[10],"text":[13],"are":[14,57,92],"annotated":[15,35],"with":[16,176,184],"disambiguated":[17],"entities":[18,33,52,84,99],"from":[19],"large":[20],"catalogs":[21],"like":[22],"Freebase.Entity":[23],"annotators":[24],"need":[25],"to":[26,70,77,83,111,164],"trained":[28],"on":[29],"sample":[30,61],"mention":[31,106],"snippets.Wikipedia":[32],"and":[34,43,55,103,150,171,187],"pages":[36],"offer":[37],"high-quality":[38],"labeled":[39],"data":[40],"for":[41,119,169],"training":[42],"evaluation.Unfortunately,":[44],"Wikipedia":[45],"features":[46],"only":[47],"one-ninth":[48],"the":[49,95,132,181,192],"number":[50],"of":[51,62,97,180],"as":[53],"Freebase,":[54,145],"these":[56],"a":[58,78,115],"highly":[59],"biased":[60],"well-connected,":[63],"frequently":[64],"mentioned":[65],"\"head\"":[66],"entities.To":[67],"bring":[68],"hope":[69],"\"tail\"":[71,170],"entities,":[72,186],"we":[73],"broaden":[74],"our":[75],"goal":[76],"second":[79],"task:":[80],"assigning":[81],"types":[82,96,110],"Freebase":[86,185],"but":[87,130],"not":[88],"Wikipedia.The":[89],"two":[90],"tasks":[91],"synergistic:":[93],"knowing":[94],"unfamiliar":[98],"helps":[100],"disambiguate":[101],"mentions,":[102],"words":[104],"contexts":[107],"help":[108],"assign":[109],"entities.We":[112,173],"present":[113],"TMI,":[114],"bipartite":[116],"graphical":[117],"model":[118],"joint":[120],"type-mention":[121],"inference.TMI":[122],"attempts":[123],"no":[124],"schema":[125],"integration":[126],"or":[127],"entity":[128],"resolution,":[129],"exploits":[131],"above-mentioned":[133],"synergy.In":[134],"experiments":[135],"involving":[136],"780,000":[137],"people":[138,143,193],"Wikipedia,":[140],"2.3":[141],"million":[142,147],"700":[146],"pages,":[149],"over":[151],"20":[152],"professional":[153],"editors,":[154],"TMI":[155],"shows":[156],"considerable":[157,189],"annotation":[158],"accuracy":[159],"improvement":[160],"(e.g.,":[161,166],"70%)":[162],"compared":[163],"baselines":[165],"46%),":[167],"especially":[168],"emerging":[172],"also":[174],"compare":[175],"Google's":[177],"recent":[178],"annotations":[179],"same":[182],"corpus":[183],"report":[188],"improvements":[190],"within":[191],"domain.":[194]},"counts_by_year":[{"year":2018,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
