{"id":"https://openalex.org/W2064983661","doi":"https://doi.org/10.1145/1401890.1401899","title":"Structured entity identification and document categorization","display_name":"Structured entity identification and document categorization","publication_year":2008,"publication_date":"2008-08-24","ids":{"openalex":"https://openalex.org/W2064983661","doi":"https://doi.org/10.1145/1401890.1401899","mag":"2064983661"},"language":"en","primary_location":{"id":"doi:10.1145/1401890.1401899","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401899","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/A5101727281","display_name":"Indrajit Bhattacharya","orcid":"https://orcid.org/0009-0004-4279-538X"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN","US"],"is_corresponding":true,"raw_author_name":"Indrajit Bhattacharya","raw_affiliation_strings":["IBM India Research Lab, New Delhi, India","IBM, India Research Lab., New Delhi, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM, India Research Lab., New Delhi, India#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033214720","display_name":"Shantanu Godbole","orcid":"https://orcid.org/0009-0001-7071-9438"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Shantanu Godbole","raw_affiliation_strings":["IBM India Research Lab, New Delhi, India","IBM, India Research Lab., New Delhi, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM, India Research Lab., New Delhi, India#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102334232","display_name":"Sachindra Joshi","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Sachindra Joshi","raw_affiliation_strings":["IBM India Research Lab, New Delhi, India","IBM, India Research Lab., New Delhi, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM, India Research Lab., New Delhi, India#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101727281"],"corresponding_institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210103279"],"apc_list":null,"apc_paid":null,"fwci":5.1485,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.95081209,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"33"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9984999895095825,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9984999895095825,"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/T11719","display_name":"Data Quality and Management","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9886999726295471,"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/computer-science","display_name":"Computer science","score":0.8297919034957886},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.823005199432373},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.7392798066139221},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7297097444534302},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5832427740097046},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5294686555862427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47306811809539795},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.4645037353038788},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.4346485435962677},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.43409016728401184},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4309545159339905},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40066301822662354},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3206602931022644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8297919034957886},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.823005199432373},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7392798066139221},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7297097444534302},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5832427740097046},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5294686555862427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47306811809539795},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.4645037353038788},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.4346485435962677},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.43409016728401184},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4309545159339905},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40066301822662354},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3206602931022644},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1401890.1401899","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401899","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1560550898","https://openalex.org/W1689241477","https://openalex.org/W1880262756","https://openalex.org/W2008896880","https://openalex.org/W2024770506","https://openalex.org/W2046020929","https://openalex.org/W2048679005","https://openalex.org/W2097089247","https://openalex.org/W2107743791","https://openalex.org/W2133236963","https://openalex.org/W2133576408","https://openalex.org/W2148019918","https://openalex.org/W2148638861","https://openalex.org/W2149684865","https://openalex.org/W2155453030","https://openalex.org/W2156543375","https://openalex.org/W2160664735","https://openalex.org/W2161228485","https://openalex.org/W2164806297","https://openalex.org/W2913340405","https://openalex.org/W2914746235","https://openalex.org/W3000438703","https://openalex.org/W4233135949","https://openalex.org/W6639619044"],"related_works":["https://openalex.org/W4396941953","https://openalex.org/W2987280934","https://openalex.org/W4241564561","https://openalex.org/W1964373579","https://openalex.org/W4249550055","https://openalex.org/W2899178742","https://openalex.org/W2070382004","https://openalex.org/W648072284","https://openalex.org/W2966683537","https://openalex.org/W4289306443"],"abstract_inverted_index":{"Traditionally,":[0],"research":[1],"in":[2,6,37,67,87,92,156],"identifying":[3],"structured":[4],"entities":[5,36,91],"documents":[7,46,109],"has":[8],"proceeded":[9],"independently":[10],"of":[11,43,62,146],"document":[12,97,139],"categorization":[13,98],"research.":[14],"In":[15,104,125],"this":[16,126],"paper,":[17,127],"we":[18,128,168],"observe":[19],"that":[20,51,170],"these":[21],"two":[22,172],"tasks":[23,173],"have":[24],"much":[25],"to":[26,35,90,101,110,114],"gain":[27],"from":[28,32,96,118,177],"each":[29,178],"other.":[30],"Apart":[31],"direct":[33,88],"references":[34,89],"a":[38,130],"database,":[39],"such":[40,58,71,102],"as":[41,72],"names":[42],"person":[44],"entities,":[45],"often":[47],"also":[48],"contain":[49],"words":[50],"are":[52],"correlated":[53],"with":[54,99],"discriminative":[55],"entity":[56,77,106,119,136],"attributes,":[57],"age-group":[59],"and":[60,85,138,165],"income-level":[61],"persons.":[63],"This":[64],"happens":[65],"naturally":[66],"many":[68],"enterprise":[69],"domains":[70],"CRM,":[73],"Banking,":[74],"etc.":[75],"Then,":[76],"identification,":[78],"which":[79],"is":[80],"typically":[81],"vulnerable":[82],"against":[83],"noise":[84],"incompleteness":[86],"documents,":[93],"can":[94,149,174],"benefit":[95,175],"respect":[100],"attributes.":[103],"return,":[105],"identification":[107,137],"enables":[108],"be":[111,150],"categorized":[112],"according":[113],"different":[115],"label-sets":[116],"arising":[117],"attributes":[120],"without":[121],"requiring":[122],"any":[123],"supervision.":[124],"propose":[129],"probabilistic":[131],"generative":[132],"model":[133,148],"for":[134],"joint":[135],"categorization.":[140],"We":[141],"show":[142],"how":[143],"the":[144,147,171,184],"parameters":[145],"estimated":[151],"using":[152,183],"an":[153,157],"EM":[154],"algorithm":[155],"unsupervised":[158],"fashion.":[159],"Using":[160],"extensive":[161],"experiments":[162],"over":[163],"real":[164],"semi-synthetic":[166],"data,":[167],"demonstrate":[169],"immensely":[176],"other":[179],"when":[180],"performed":[181],"jointly":[182],"proposed":[185],"model.":[186]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}