{"id":"https://openalex.org/W2162262658","doi":"https://doi.org/10.1145/1390156.1390256","title":"Semi-supervised learning of compact document representations with deep networks","display_name":"Semi-supervised learning of compact document representations with deep networks","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W2162262658","doi":"https://doi.org/10.1145/1390156.1390256","mag":"2162262658"},"language":"en","primary_location":{"id":"doi:10.1145/1390156.1390256","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390156.1390256","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 international conference on Machine learning - ICML '08","raw_type":"proceedings-article"},"type":"conference-paper","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/A5109358395","display_name":"Marc ' Aurelio Ranzato","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marc' Aurelio Ranzato","raw_affiliation_strings":["New York University, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University, New York, NY","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043531170","display_name":"Martin Szummer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Martin Szummer","raw_affiliation_strings":["Microsoft Research Cambridge, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":223,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"792","last_page":"799"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9969000220298767,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.806384801864624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7174669504165649},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6607004404067993},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.649379312992096},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6337658166885376},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.612188994884491},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6066839098930359},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.5540298819541931},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.48680850863456726},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4245012104511261},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3953019678592682},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11065071821212769}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.806384801864624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7174669504165649},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6607004404067993},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.649379312992096},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6337658166885376},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.612188994884491},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6066839098930359},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.5540298819541931},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.48680850863456726},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4245012104511261},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3953019678592682},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11065071821212769},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1390156.1390256","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390156.1390256","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 international conference on Machine learning - ICML '08","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1612003148","https://openalex.org/W1880262756","https://openalex.org/W2014415866","https://openalex.org/W2079968649","https://openalex.org/W2100495367","https://openalex.org/W2108665656","https://openalex.org/W2110798204","https://openalex.org/W2116064496","https://openalex.org/W2136922672","https://openalex.org/W2147152072","https://openalex.org/W2162724919","https://openalex.org/W2605998369","https://openalex.org/W2613634265","https://openalex.org/W2913932916","https://openalex.org/W2914484425"],"related_works":["https://openalex.org/W2053389710","https://openalex.org/W4238415164","https://openalex.org/W2154282042","https://openalex.org/W2039135287","https://openalex.org/W2886642366","https://openalex.org/W2183607598","https://openalex.org/W2568006847","https://openalex.org/W1977123279","https://openalex.org/W2887027901","https://openalex.org/W1973399557"],"abstract_inverted_index":{"Finding":[0],"good":[1],"representations":[2,56,82],"of":[3,25,83],"text":[4,54],"documents":[5],"is":[6,20,101],"crucial":[7],"in":[8,28],"information":[9,90],"retrieval":[10],"and":[11,91],"classification":[12],"systems.":[13],"Today":[14],"the":[15,29],"most":[16],"popular":[17],"document":[18,55],"representation":[19,32],"based":[21,57],"on":[22,58,75],"a":[23,66,106],"vector":[24],"word":[26,93],"counts":[27],"document.":[30],"This":[31],"neither":[33],"captures":[34],"dependencies":[35],"between":[36],"related":[37],"words,":[38],"nor":[39],"handles":[40],"synonyms":[41],"or":[42],"polysemous":[43],"words.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"propose":[49],"an":[50],"algorithm":[51],"to":[52,64,103],"learn":[53],"semi-supervised":[59],"autoencoders":[60],"that":[61,99],"are":[62],"stacked":[63],"form":[65],"deep":[67],"network.":[68],"The":[69],"model":[70],"can":[71],"be":[72],"trained":[73],"efficiently":[74],"partially":[76],"labeled":[77,108],"corpora,":[78],"producing":[79],"very":[80],"compact":[81],"documents,":[84],"while":[85],"retaining":[86],"as":[87,95],"much":[88],"class":[89],"joint":[92],"statistics":[94],"possible.":[96],"We":[97],"show":[98],"it":[100],"advantageous":[102],"exploit":[104],"even":[105],"few":[107],"samples":[109],"during":[110],"training.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":24},{"year":2018,"cited_by_count":26},{"year":2017,"cited_by_count":28},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":25},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}