{"id":"https://openalex.org/W2963274420","doi":"https://doi.org/10.18653/v1/w17-2614","title":"DocTag2Vec: An Embedding Based Multi-label Learning Approach for Document Tagging","display_name":"DocTag2Vec: An Embedding Based Multi-label Learning Approach for Document Tagging","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2963274420","doi":"https://doi.org/10.18653/v1/w17-2614","mag":"2963274420"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-2614","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2614","pdf_url":"https://www.aclweb.org/anthology/W17-2614.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Representation Learning for NLP","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-2614.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100320969","display_name":"Sheng Chen","orcid":"https://orcid.org/0000-0001-6882-600X"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]},{"id":"https://openalex.org/I4210101327","display_name":"Twin Cities Orthopedics","ror":"https://ror.org/01en4s460","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210101327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheng Chen","raw_affiliation_strings":["University of Minnesota-Twin Cities, Minneapolis, MN 55455, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Minnesota-Twin Cities, Minneapolis, MN 55455, USA","institution_ids":["https://openalex.org/I130238516","https://openalex.org/I4210101327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029379554","display_name":"Akshay Soni","orcid":"https://orcid.org/0000-0002-3518-7667"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akshay Soni","raw_affiliation_strings":["Yahoo Research, Sunnyvale, CA 94089, USA and"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research, Sunnyvale, CA 94089, USA and","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113662152","display_name":"Aasish Pappu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aasish Pappu","raw_affiliation_strings":["New York, NY 10036, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York, NY 10036, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067997502","display_name":"Yashar Mehdad","orcid":null},"institutions":[{"id":"https://openalex.org/I106110158","display_name":"Bay Area Air Quality Management District","ror":"https://ror.org/04431t173","country_code":"US","type":"government","lineage":["https://openalex.org/I106110158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yashar Mehdad","raw_affiliation_strings":["Airbnb, San Francisco, CA 94103, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Airbnb, San Francisco, CA 94103, USA","institution_ids":["https://openalex.org/I106110158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6462,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.89003387,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"111","last_page":"120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9995999932289124,"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":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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":0.9980999827384949,"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":0.8518331050872803},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.8210097551345825},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6350778937339783},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5985672473907471},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.549992561340332},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5436503291130066},{"id":"https://openalex.org/keywords/bag-of-words-model","display_name":"Bag-of-words model","score":0.5392805933952332},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.483675092458725},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4455646276473999},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42173415422439575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41792115569114685},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3276195526123047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8518331050872803},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.8210097551345825},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6350778937339783},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5985672473907471},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.549992561340332},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5436503291130066},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.5392805933952332},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.483675092458725},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4455646276473999},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42173415422439575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41792115569114685},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3276195526123047},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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:10.18653/v1/w17-2614","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2614","pdf_url":"https://www.aclweb.org/anthology/W17-2614.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Representation Learning for NLP","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-2614","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2614","pdf_url":"https://www.aclweb.org/anthology/W17-2614.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Representation Learning for NLP","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963274420.pdf","grobid_xml":"https://content.openalex.org/works/W2963274420.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W21006490","https://openalex.org/W35899105","https://openalex.org/W36903255","https://openalex.org/W71795751","https://openalex.org/W174427690","https://openalex.org/W303217050","https://openalex.org/W1115028143","https://openalex.org/W1494527657","https://openalex.org/W1546425806","https://openalex.org/W1570587036","https://openalex.org/W1834987204","https://openalex.org/W1843891098","https://openalex.org/W1940008012","https://openalex.org/W1975719446","https://openalex.org/W1976859382","https://openalex.org/W1977991182","https://openalex.org/W1988157164","https://openalex.org/W2045865594","https://openalex.org/W2051093690","https://openalex.org/W2056088289","https://openalex.org/W2068074736","https://openalex.org/W2090041477","https://openalex.org/W2107269684","https://openalex.org/W2115119296","https://openalex.org/W2115613106","https://openalex.org/W2125846172","https://openalex.org/W2131744502","https://openalex.org/W2150907923","https://openalex.org/W2153579005","https://openalex.org/W2167143366","https://openalex.org/W2170422946","https://openalex.org/W2183087644","https://openalex.org/W2250879510","https://openalex.org/W2252215182","https://openalex.org/W2296283641","https://openalex.org/W2950170811","https://openalex.org/W2951238624","https://openalex.org/W2962756421","https://openalex.org/W2962902328","https://openalex.org/W2962965405","https://openalex.org/W2963312446","https://openalex.org/W2964266863","https://openalex.org/W3194416009","https://openalex.org/W4294170691","https://openalex.org/W4297571622","https://openalex.org/W6600223405","https://openalex.org/W6600599538"],"related_works":["https://openalex.org/W2509219942","https://openalex.org/W2912231714","https://openalex.org/W3175524270","https://openalex.org/W3092569358","https://openalex.org/W4251594503","https://openalex.org/W4226211987","https://openalex.org/W4297609205","https://openalex.org/W3070760781","https://openalex.org/W2803113975","https://openalex.org/W3200784702"],"abstract_inverted_index":{"Tagging":[0],"news":[1],"articles":[2,26],"or":[3],"blog":[4],"posts":[5],"with":[6,112],"relevant":[7],"tags":[8,81,98],"from":[9],"a":[10,42,83],"collection":[11],"of":[12,25,66,77,116,128,134,143],"predefined":[13],"ones":[14],"is":[15],"coined":[16],"as":[17,33],"document":[18],"tagging":[19,24],"in":[20,82,121],"this":[21,38,51],"work.":[22],"Accurate":[23],"can":[27],"benefit":[28],"several":[29,150],"downstream":[30],"applications":[31],"such":[32],"recommendation":[34],"and":[35,57,68,80,89,120,131,152],"search.":[36],"In":[37,70,102],"work,":[39],"we":[40,72,146],"propose":[41],"novel":[43],"yet":[44],"simple":[45,92],"approach":[46],"called":[47],"DocTag2Vec":[48,109],"to":[49,96,104],"accomplish":[50],"task.":[52],"We":[53],"substantially":[54],"extend":[55],"Word2Vec":[56],"Doc2Vec":[58],"-two":[59],"popular":[60],"models":[61],"for":[62,99],"learning":[63,107,127],"distributed":[64],"representation":[65,76],"words":[67],"documents.":[69,101],"DocTag2Vec,":[71],"simultaneously":[73],"learn":[74],"the":[75,91,126,132,141],"words,":[78],"documents,":[79],"joint":[84],"vector":[85],"space":[86],"during":[87],"training,":[88],"employ":[90],"k-nearest":[93],"neighbor":[94],"search":[95],"predict":[97],"unseen":[100],"contrast":[103],"previous":[105],"multi-label":[106],"methods,":[108],"directly":[110],"deals":[111],"raw":[113],"text":[114],"instead":[115],"provided":[117],"feature":[118],"vector,":[119],"addition,":[122],"enjoys":[123],"advantages":[124],"like":[125],"tag":[129],"representation,":[130],"ability":[133],"handling":[135],"newly":[136],"created":[137],"tags.":[138],"To":[139],"demonstrate":[140],"effectiveness":[142],"our":[144],"approach,":[145],"conduct":[147],"experiments":[148],"on":[149],"datasets":[151],"show":[153],"promising":[154],"results":[155],"against":[156],"state-of-the-art":[157],"methods.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}