{"id":"https://openalex.org/W2005358940","doi":"https://doi.org/10.1145/2063576.2063962","title":"Towards noise-resilient document modeling","display_name":"Towards noise-resilient document modeling","publication_year":2011,"publication_date":"2011-10-24","ids":{"openalex":"https://openalex.org/W2005358940","doi":"https://doi.org/10.1145/2063576.2063962","mag":"2005358940"},"language":"en","primary_location":{"id":"doi:10.1145/2063576.2063962","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063962","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international 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/A5027201139","display_name":"Tao Yang","orcid":"https://orcid.org/0000-0001-6265-6177"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tao Yang","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100405086","display_name":"Dongwon Lee","orcid":"https://orcid.org/0000-0001-8371-7629"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongwon Lee","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5027201139"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":0.8805,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.79559934,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"200","issue":null,"first_page":"2345","last_page":"2348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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/T13083","display_name":"Advanced Text Analysis Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.8630064725875854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7653906345367432},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6296291351318359},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6248729228973389},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.613757312297821},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5849546194076538},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.5153526663780212},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5124586224555969},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4916847348213196},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48331665992736816},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4433422386646271},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.43909192085266113},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.41964399814605713},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40363389253616333},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3740287721157074},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3480435609817505},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.07202926278114319}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.8630064725875854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7653906345367432},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6296291351318359},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6248729228973389},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.613757312297821},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5849546194076538},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.5153526663780212},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5124586224555969},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4916847348213196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48331665992736816},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4433422386646271},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.43909192085266113},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.41964399814605713},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40363389253616333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3740287721157074},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3480435609817505},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07202926278114319},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2063576.2063962","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063962","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.228.2589","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.228.2589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://pike.psu.edu/publications/cikm11.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1601566332","https://openalex.org/W1880262756","https://openalex.org/W2115014674"],"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":{"We":[0],"introduce":[1],"a":[2,58],"generative":[3],"probabilistic":[4],"document":[5,20],"model":[6,23,84],"based":[7],"on":[8],"latent":[9],"Dirichlet":[10],"allocation":[11],"(LDA),":[12],"to":[13,68],"deal":[14],"with":[15],"textual":[16],"errors":[17],"in":[18,66],"the":[19,27,53,62,70,79],"collection.":[21],"Our":[22],"is":[24,50,85],"inspired":[25],"by":[26,56],"fact":[28],"that":[29],"most":[30],"large-scale":[31],"text":[32,74],"data":[33,92],"are":[34],"machine-generated":[35],"and":[36,90],"thus":[37],"inevitably":[38],"contain":[39],"many":[40],"types":[41],"of":[42,72,81],"noise.":[43],"The":[44],"new":[45],"model,":[46],"termed":[47],"as":[48],"TE-LDA,":[49],"developed":[51],"from":[52],"traditional":[54],"LDA":[55],"adding":[57],"switch":[59],"variable":[60],"into":[61],"term":[63],"generation":[64],"process":[65],"order":[67],"tackle":[69],"issue":[71],"noisy":[73],"data.":[75],"Through":[76],"extensive":[77],"experiments,":[78],"efficacy":[80],"our":[82],"proposed":[83],"validated":[86],"using":[87],"both":[88],"real":[89],"synthetic":[91],"sets.":[93]},"counts_by_year":[{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}