{"id":"https://openalex.org/W3114079967","doi":"https://doi.org/10.1145/3437963.3441810","title":"DeepXML: A Deep Extreme Multi-Label Learning Framework Applied to Short Text Documents","display_name":"DeepXML: A Deep Extreme Multi-Label Learning Framework Applied to Short Text Documents","publication_year":2021,"publication_date":"2021-03-06","ids":{"openalex":"https://openalex.org/W3114079967","doi":"https://doi.org/10.1145/3437963.3441810","mag":"3114079967"},"language":"en","primary_location":{"id":"doi:10.1145/3437963.3441810","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437963.3441810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2111.06685","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081553743","display_name":"Kunal Dahiya","orcid":"https://orcid.org/0000-0002-1500-0295"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Kunal Dahiya","raw_affiliation_strings":["IIT Delhi, Delhi, India"],"affiliations":[{"raw_affiliation_string":"IIT Delhi, Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059937402","display_name":"Deepak Saini","orcid":"https://orcid.org/0000-0002-6057-4351"},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Deepak Saini","raw_affiliation_strings":["Microsoft Research, Bengaluru, India"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Bengaluru, India","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101944479","display_name":"Anshul Mittal","orcid":"https://orcid.org/0000-0002-4137-0126"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anshul Mittal","raw_affiliation_strings":["IIT Delhi, Delhi, India"],"affiliations":[{"raw_affiliation_string":"IIT Delhi, Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013478465","display_name":"Ankush Shaw","orcid":null},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ankush Shaw","raw_affiliation_strings":["IIT Delhi, Delhi, India"],"affiliations":[{"raw_affiliation_string":"IIT Delhi, Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004283227","display_name":"Kushal Dave","orcid":"https://orcid.org/0000-0001-5963-1470"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kushal Dave","raw_affiliation_strings":["Microsoft, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"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/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akshay Soni","raw_affiliation_strings":["Microsoft, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105352990","display_name":"Himanshu Jain","orcid":"https://orcid.org/0000-0003-4324-8666"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Himanshu Jain","raw_affiliation_strings":["IIT Delhi, Delhi, India"],"affiliations":[{"raw_affiliation_string":"IIT Delhi, Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001668151","display_name":"Sumeet Agarwal","orcid":"https://orcid.org/0000-0002-5714-3921"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sumeet Agarwal","raw_affiliation_strings":["IIT Delhi, Delhi, India"],"affiliations":[{"raw_affiliation_string":"IIT Delhi, Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051880496","display_name":"Manik Varma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Manik Varma","raw_affiliation_strings":["Microsoft Research & IIT Delhi, Bengaluru, India"],"affiliations":[{"raw_affiliation_string":"Microsoft Research & IIT Delhi, Bengaluru, India","institution_ids":["https://openalex.org/I4210124949","https://openalex.org/I68891433"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5081553743"],"corresponding_institution_ids":["https://openalex.org/I68891433"],"apc_list":null,"apc_paid":null,"fwci":6.4306,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.97067488,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"39"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9975000023841858,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9932000041007996,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7756446003913879},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5464580655097961},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.47366863489151},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4652928113937378},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39351725578308105}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7756446003913879},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5464580655097961},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47366863489151},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4652928113937378},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39351725578308105}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3437963.3441810","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437963.3441810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2111.06685","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.06685","pdf_url":"https://arxiv.org/pdf/2111.06685","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2111.06685","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.06685","pdf_url":"https://arxiv.org/pdf/2111.06685","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W1546425806","https://openalex.org/W1834987204","https://openalex.org/W1892593501","https://openalex.org/W2068074736","https://openalex.org/W2118206599","https://openalex.org/W2136189984","https://openalex.org/W2139273454","https://openalex.org/W2153190022","https://openalex.org/W2164295002","https://openalex.org/W2165698076","https://openalex.org/W2183087644","https://openalex.org/W2194775991","https://openalex.org/W2318810549","https://openalex.org/W2362855512","https://openalex.org/W2437817353","https://openalex.org/W2461743311","https://openalex.org/W2520348554","https://openalex.org/W2568082647","https://openalex.org/W2593236586","https://openalex.org/W2739996966","https://openalex.org/W2744136723","https://openalex.org/W2753300133","https://openalex.org/W2782759081","https://openalex.org/W2785678896","https://openalex.org/W2788125153","https://openalex.org/W2804456057","https://openalex.org/W2809205451","https://openalex.org/W2809577315","https://openalex.org/W2886305600","https://openalex.org/W2896457183","https://openalex.org/W2899313146","https://openalex.org/W2906963924","https://openalex.org/W2914260367","https://openalex.org/W2914323790","https://openalex.org/W2921113176","https://openalex.org/W2945444092","https://openalex.org/W2945456403","https://openalex.org/W2950110558","https://openalex.org/W2950352656","https://openalex.org/W2950364356","https://openalex.org/W2950801772","https://openalex.org/W2962998615","https://openalex.org/W2963469388","https://openalex.org/W2963626623","https://openalex.org/W2963836885","https://openalex.org/W2963854351","https://openalex.org/W2964240234","https://openalex.org/W2964818371","https://openalex.org/W2965373594","https://openalex.org/W2970449868","https://openalex.org/W2970641574","https://openalex.org/W2972801466","https://openalex.org/W2982392466","https://openalex.org/W2990176236","https://openalex.org/W2996064239","https://openalex.org/W3005296017","https://openalex.org/W3037422790","https://openalex.org/W3039729104","https://openalex.org/W3080802002","https://openalex.org/W3095787923","https://openalex.org/W3096437212","https://openalex.org/W3117196003","https://openalex.org/W3152616003","https://openalex.org/W3156044630","https://openalex.org/W3189721578","https://openalex.org/W3194416009","https://openalex.org/W4288279338","https://openalex.org/W4294170691","https://openalex.org/W4297790600","https://openalex.org/W6602670149","https://openalex.org/W6631228298","https://openalex.org/W6819060087"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W4360585206","https://openalex.org/W4321369474","https://openalex.org/W4285208911","https://openalex.org/W3082895349","https://openalex.org/W4213079790","https://openalex.org/W2248239756","https://openalex.org/W4323565446"],"abstract_inverted_index":{"Scalability":[0],"and":[1,66,88,103,142,190],"accuracy":[2,87],"are":[3],"well":[4],"recognized":[5],"challenges":[6,47],"in":[7,186,198],"deep":[8,51,110],"extreme":[9,52,111],"multi-label":[10,53],"learning":[11],"where":[12,181],"the":[13,26,41,50,72,94,157],"objective":[14],"is":[15,202],"to":[16,77,106,131,153,173,177],"train":[17,107,123],"architectures":[18],"for":[19,71,138,161],"automatically":[20],"annotating":[21],"a":[22,79,162],"data":[23,143],"point":[24],"with":[25,83],"most":[27],"relevant":[28],"subset":[29],"of":[30,60,81,140,164],"labels":[31,134],"from":[32,169],"an":[33],"extremely":[34],"large":[35],"label":[36],"set.":[37],"This":[38,150],"paper":[39],"develops":[40],"DeepXML":[42,76,92],"framework":[43],"that":[44,97],"addresses":[45],"these":[46],"by":[48],"decomposing":[49],"task":[54],"into":[55],"four":[56,73],"simpler":[57],"sub-tasks":[58,74],"each":[59],"which":[61],"can":[62],"be":[63,99,154],"trained":[64],"accurately":[65],"efficiently.":[67],"Choosing":[68],"different":[69],"components":[70],"allows":[75],"generate":[78],"family":[80],"algorithms":[82],"varying":[84],"trade-offs":[85],"between":[86],"scalability.":[89],"In":[90],"particular,":[91],"yields":[93],"Astec":[95,119,152],"algorithm":[96],"could":[98,120],"2-12%":[100],"more":[101],"accurate":[102],"5-30x":[104],"faster":[105],"than":[108],"leading":[109],"classifiers":[112],"on":[113,124,147,156],"publically":[114],"available":[115,203],"short":[116,126,165],"text":[117,127,166],"datasets.":[118],"also":[121],"efficiently":[122],"Bing":[125,158],"datasets":[128],"containing":[129],"up":[130],"62":[132],"million":[133],"while":[135],"making":[136],"predictions":[137],"billions":[139],"users":[141],"points":[144],"per":[145],"day":[146],"commodity":[148],"hardware.":[149],"allowed":[151],"deployed":[155],"search":[159],"engine":[160],"number":[163],"applications":[167],"ranging":[168],"matching":[170],"user":[171],"queries":[172],"advertiser":[174],"bid":[175],"phrases":[176],"showing":[178],"personalized":[179],"ads":[180],"it":[182],"yielded":[183],"significant":[184],"gains":[185],"click-through-rates,":[187],"coverage,":[188],"revenue":[189],"other":[191],"online":[192],"metrics":[193],"over":[194],"state-of-the-art":[195],"techniques":[196],"currently":[197],"production.":[199],"DeepXML's":[200],"code":[201],"at":[204],"https://github.com/Extreme-classification/deepxml":[205]},"counts_by_year":[{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":13},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}