{"id":"https://openalex.org/W1986715529","doi":"https://doi.org/10.1145/1458082.1458236","title":"A generative retrieval model for structured documents","display_name":"A generative retrieval model for structured documents","publication_year":2008,"publication_date":"2008-10-26","ids":{"openalex":"https://openalex.org/W1986715529","doi":"https://doi.org/10.1145/1458082.1458236","mag":"1986715529"},"language":"en","primary_location":{"id":"doi:10.1145/1458082.1458236","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","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/A5089791620","display_name":"Le Zhao","orcid":"https://orcid.org/0000-0002-1213-1126"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Le Zhao","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009879041","display_name":"Jamie Callan","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jamie Callan","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5089791620"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":7.6138,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.96789032,"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":"1163","last_page":"1172"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9994999766349792,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9994999766349792,"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":0.9987999796867371,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9916999936103821,"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":0.8472789525985718},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.7357463836669922},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7057998776435852},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.5559402704238892},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5070197582244873},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5070016384124756},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4653495252132416},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.44886577129364014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4244159460067749},{"id":"https://openalex.org/keywords/divergence-from-randomness-model","display_name":"Divergence-from-randomness model","score":0.41538047790527344},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41514450311660767},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.3620043396949768},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.08725276589393616}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8472789525985718},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.7357463836669922},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7057998776435852},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.5559402704238892},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5070197582244873},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5070016384124756},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4653495252132416},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.44886577129364014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4244159460067749},{"id":"https://openalex.org/C149189445","wikidata":"https://www.wikidata.org/wiki/Q5283894","display_name":"Divergence-from-randomness model","level":3,"score":0.41538047790527344},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41514450311660767},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.3620043396949768},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.08725276589393616},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1458082.1458236","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.46000000834465027}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W238053929","https://openalex.org/W1519066168","https://openalex.org/W1571866607","https://openalex.org/W1586403433","https://openalex.org/W1985554184","https://openalex.org/W2025910815","https://openalex.org/W2065658522","https://openalex.org/W2087663869","https://openalex.org/W2093390569","https://openalex.org/W2098643647","https://openalex.org/W2116192173","https://openalex.org/W2119788759","https://openalex.org/W2134557008","https://openalex.org/W2136542423","https://openalex.org/W2166282252","https://openalex.org/W2271772693","https://openalex.org/W2916104554","https://openalex.org/W4206765718","https://openalex.org/W4240913316","https://openalex.org/W4251560691"],"related_works":["https://openalex.org/W2888805565","https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W4293863151","https://openalex.org/W3159709618","https://openalex.org/W2611137333","https://openalex.org/W3005513013"],"abstract_inverted_index":{"Structured":[0,16],"documents":[1,17],"contain":[2],"elements":[3],"defined":[4],"by":[5,11,44,75],"the":[6,29,33,63,70,82,88,115,136],"author(s)":[7],"and":[8,32,94,107,131,148],"annotations":[9],"assigned":[10],"other":[12],"people":[13],"or":[14,40],"processes.":[15],"pose":[18],"challenges":[19],"for":[20],"probabilistic":[21],"retrieval":[22,56,106,109,118,139,143],"models":[23],"when":[24],"there":[25],"are":[26,90,98],"mismatches":[27],"between":[28],"structured":[30,117,134,138],"query":[31],"actual":[34],"structure":[35,42,77],"in":[36],"a":[37,53],"relevant":[38],"document":[39],"erroneous":[41],"introduced":[43],"an":[45],"annotator.":[46],"This":[47,66],"paper":[48],"makes":[49],"three":[50],"contributions.":[51],"First,":[52],"new":[54,67],"generative":[55],"model":[57,68,74,89,119,140],"is":[58,120],"proposed":[59,137],"to":[60],"deal":[61],"with":[62,103,132],"mismatch":[64],"problem.":[65],"extends":[69],"basic":[71],"keyword":[72,142],"language":[73],"treating":[76],"as":[78],"hidden":[79],"variable":[80],"during":[81],"generation":[83],"process.":[84],"Second,":[85],"variations":[86],"of":[87],"compared.":[91],"Third,":[92],"term-level":[93],"structure-level":[95],"smoothing":[96,125],"strategies":[97],"studied.":[99],"Evaluation":[100],"was":[101],"conducted":[102],"INEX":[104,149],"XML":[105],"question-answering":[108],"tasks.":[110],"Experimental":[111],"results":[112],"indicate":[113],"that":[114],"optimal":[116],"task":[121],"dependent,":[122],"two-level":[123,128],"Dirichlet":[124],"significantly":[126],"outperforms":[127,141],"Jelinek-Mercer":[129],"smoothing,":[130],"accurate":[133],"queries,":[135],"significantly,":[144],"on":[145],"both":[146],"QA":[147],"datasets.":[150]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"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"}