{"id":"https://openalex.org/W2538769922","doi":"https://doi.org/10.1145/2983323.2983752","title":"Semi-supervised Multi-Label Topic Models for Document Classification and Sentence Labeling","display_name":"Semi-supervised Multi-Label Topic Models for Document Classification and Sentence Labeling","publication_year":2016,"publication_date":"2016-10-24","ids":{"openalex":"https://openalex.org/W2538769922","doi":"https://doi.org/10.1145/2983323.2983752","mag":"2538769922"},"language":"en","primary_location":{"id":"doi:10.1145/2983323.2983752","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2983323.2983752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International on 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/A5075566770","display_name":"Hossein Soleimani","orcid":"https://orcid.org/0000-0002-3086-8463"},"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":"Hossein Soleimani","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101739086","display_name":"David J. Miller","orcid":"https://orcid.org/0000-0001-8848-1643"},"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":"David J. Miller","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"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/A5075566770"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":5.5693,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.96140962,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"105","last_page":"114"},"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/T11550","display_name":"Text and Document Classification Technologies","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":0.996999979019165,"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":0.8050200939178467},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6862706542015076},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6456494331359863},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5560551881790161},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.549156129360199},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.531934380531311},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5247535705566406},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.47290313243865967},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4258248805999756},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3646637797355652}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8050200939178467},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6862706542015076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6456494331359863},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5560551881790161},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.549156129360199},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.531934380531311},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5247535705566406},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47290313243865967},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4258248805999756},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3646637797355652},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2983323.2983752","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2983323.2983752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W56136284","https://openalex.org/W190008395","https://openalex.org/W621546036","https://openalex.org/W1516111018","https://openalex.org/W1552847225","https://openalex.org/W1611774714","https://openalex.org/W1880262756","https://openalex.org/W1947594277","https://openalex.org/W1969486090","https://openalex.org/W1982508956","https://openalex.org/W2001082470","https://openalex.org/W2010792435","https://openalex.org/W2016015339","https://openalex.org/W2020842694","https://openalex.org/W2028962062","https://openalex.org/W2034315836","https://openalex.org/W2076623641","https://openalex.org/W2098162425","https://openalex.org/W2103673731","https://openalex.org/W2108745803","https://openalex.org/W2110119381","https://openalex.org/W2122683976","https://openalex.org/W2130747910","https://openalex.org/W2137054688","https://openalex.org/W2137576513","https://openalex.org/W2144630266","https://openalex.org/W2156693754","https://openalex.org/W2157589241","https://openalex.org/W2161050705","https://openalex.org/W2170240176","https://openalex.org/W2174706414","https://openalex.org/W2478027467","https://openalex.org/W2486125749","https://openalex.org/W2503956817","https://openalex.org/W2950118368","https://openalex.org/W2954040150","https://openalex.org/W3029645440","https://openalex.org/W4252381709","https://openalex.org/W4301909677","https://openalex.org/W6638674303","https://openalex.org/W6842097421"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W4323323165","https://openalex.org/W2745033168"],"abstract_inverted_index":{"Extracting":[0],"parts":[1],"of":[2,43,50,56,61,64,66,81],"a":[3,8,12,19,41,78,87,132,149],"text":[4],"document":[5,27,58,168],"relevant":[6],"to":[7,166],"class":[9,30,99],"label":[10,54,110,144],"is":[11,37,184],"critical":[13],"information":[14],"retrieval":[15],"task.":[16],"We":[17,130],"propose":[18],"semi-supervised":[20],"multi-label":[21],"topic":[22],"model":[23,121],"for":[24,103,112,138,180],"jointly":[25],"achieving":[26],"and":[28,98,108,169],"sentence-level":[29,170],"inferences.":[31],"Under":[32],"our":[33,120,158,182],"model,":[34,85],"each":[35,113],"sentence":[36,114],"associated":[38],"with":[39,52,164],"only":[40],"subset":[42],"the":[44,53,57,59,62,91,142],"document's":[45],"labels":[46,63,102,127],"(including":[47],"possibly":[48],"none":[49],"them),":[51],"set":[55,80,176],"union":[60],"all":[65,147],"its":[67],"sentences.":[68,129],"For":[69,118],"training,":[70],"we":[71],"use":[72],"both":[73,167],"labeled":[74],"documents,":[75,107],"and,":[76],"typically,":[77],"larger":[79],"unlabeled":[82],"documents.":[83],"Our":[84,154],"in":[86,115],"semisupervised":[88],"fashion,":[89],"discovers":[90],"topics":[92,97],"present,":[93],"learns":[94],"associations":[95,111],"between":[96],"labels,":[100],"predicts":[101],"new":[104],"(or":[105],"unlabeled)":[106],"determines":[109],"every":[116],"document.":[117],"learning,":[119],"does":[122],"not":[123],"require":[124],"any":[125],"ground-truth":[126],"on":[128],"develop":[131],"Hamiltonian":[133],"Monte":[134],"Carlo":[135],"based":[136],"algorithm":[137],"efficiently":[139],"sampling":[140],"from":[141,186],"joint":[143],"distribution":[145],"over":[146],"sentences,":[148],"very":[150],"high-dimensional":[151],"discrete":[152],"space.":[153],"experiments":[155,183],"show":[156],"that":[157],"approach":[159],"outperforms":[160],"several":[161],"benchmark":[162],"methods":[163],"respect":[165],"classification,":[171],"as":[172,174],"well":[173],"test":[175],"log-likelihood.":[177],"All":[178],"code":[179],"replicating":[181],"available":[185],"https://github.com/hsoleimani/MLTM.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}