{"id":"https://openalex.org/W3155224787","doi":"https://doi.org/10.1145/3442381.3450114","title":"Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networks","display_name":"Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networks","publication_year":2021,"publication_date":"2021-04-19","ids":{"openalex":"https://openalex.org/W3155224787","doi":"https://doi.org/10.1145/3442381.3450114","mag":"3155224787"},"language":"en","primary_location":{"id":"doi:10.1145/3442381.3450114","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3450114","pdf_url":null,"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 Web Conference 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3442381.3450114","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022999126","display_name":"Xinyang Zhang","orcid":"https://orcid.org/0000-0001-6474-682X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xinyang Zhang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011355966","display_name":"Chenwei Zhang","orcid":"https://orcid.org/0000-0002-0606-3649"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenwei Zhang","raw_affiliation_strings":["Amazon, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088720980","display_name":"Xin Dong","orcid":"https://orcid.org/0000-0001-8727-8088"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Luna Dong","raw_affiliation_strings":["Amazon, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039500313","display_name":"Jingbo Shang","orcid":"https://orcid.org/0000-0002-7249-4404"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingbo Shang","raw_affiliation_strings":["University of California, San Diego, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019539533","display_name":"Jiawei Han","orcid":"https://orcid.org/0000-0002-3629-2696"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiawei Han","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5022999126"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":1.4957,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85335216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3258","last_page":"3268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998999834060669,"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/T11550","display_name":"Text and Document Classification Technologies","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/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"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":0.9914000034332275,"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":0.8122216463088989},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6387384533882141},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.619683027267456},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6194190979003906},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5653988122940063},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.5389834642410278},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5226011872291565},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5005033016204834},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4818600118160248},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4505152106285095},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4241122007369995},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4115399122238159},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3264871835708618},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.21520009636878967}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8122216463088989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6387384533882141},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.619683027267456},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6194190979003906},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5653988122940063},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.5389834642410278},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5226011872291565},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5005033016204834},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4818600118160248},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4505152106285095},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4241122007369995},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4115399122238159},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3264871835708618},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.21520009636878967},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3442381.3450114","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3450114","pdf_url":null,"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 Web Conference 2021","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3442381.3450114","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3450114","pdf_url":null,"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 Web Conference 2021","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2048679005","https://openalex.org/W2086254934","https://openalex.org/W2095779006","https://openalex.org/W2101210369","https://openalex.org/W2115733720","https://openalex.org/W2118314245","https://openalex.org/W2133299088","https://openalex.org/W2133556223","https://openalex.org/W2170344111","https://openalex.org/W2432717477","https://openalex.org/W2593560537","https://openalex.org/W2601450892","https://openalex.org/W2740934577","https://openalex.org/W2747329762","https://openalex.org/W2890931111","https://openalex.org/W2893359107","https://openalex.org/W2962369866","https://openalex.org/W2962946486","https://openalex.org/W2963157208","https://openalex.org/W2963545917","https://openalex.org/W2971296908","https://openalex.org/W2989514282","https://openalex.org/W3021208824","https://openalex.org/W3023960840","https://openalex.org/W3035055211","https://openalex.org/W3035568641","https://openalex.org/W3039500550","https://openalex.org/W3081146346","https://openalex.org/W3099053576","https://openalex.org/W3101543043","https://openalex.org/W3101606352","https://openalex.org/W3106109117","https://openalex.org/W3127901963","https://openalex.org/W4239019441"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2392768766","https://openalex.org/W2965546495","https://openalex.org/W2058118494","https://openalex.org/W2382615723","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W4311804456","https://openalex.org/W3103844505"],"abstract_inverted_index":{"Text":[0],"categorization":[1,129,201],"is":[2,233],"an":[3,221],"essential":[4],"task":[5],"in":[6,25],"Web":[7,13,56],"content":[8],"analysis.":[9],"Considering":[10],"the":[11,21,31,55,69,102,133,171,197,240],"ever-evolving":[12],"data":[14,105],"and":[15,89,107,115,154,175],"new":[16],"emerging":[17],"categories,":[18,205],"instead":[19],"of":[20,43,101,223],"laborious":[22],"supervised":[23,128,241],"setting,":[24],"this":[26],"paper,":[27],"we":[28,137],"focus":[29],"on":[30,192,245],"minimally-supervised":[32],"setting":[33],"that":[34,51,209],"aims":[35],"to":[36],"categorize":[37],"documents":[38,45,78,214],"effectively,":[39],"with":[40,79,142,203],"a":[41,72,95,98,109,123,147,155],"couple":[42],"seed":[44,213],"annotated":[46],"per":[47,215],"category.":[48],"We":[49,120,188],"recognize":[50],"texts":[52],"collected":[53],"from":[54,132,170,239],"are":[57],"often":[58],"structure-rich,":[59],"i.e.,":[60],"accompanied":[61],"by":[62,130,182],"various":[63],"metadata.":[64],"One":[65],"can":[66,219],"easily":[67],"organize":[68],"corpus":[70],"into":[71],"text-rich":[73,134],"network,":[74],"joining":[75],"raw":[76],"text":[77,148,152],"document":[80,173],"attributes,":[81],"high-quality":[82],"phrases,":[83],"label":[84],"surface":[85],"names":[86],"as":[87,92],"nodes,":[88],"their":[90],"associations":[91],"edges.":[93],"Such":[94],"network":[96,156,162],"provides":[97],"holistic":[99],"view":[100],"corpus\u2019":[103],"heterogeneous":[104],"sources":[106],"enables":[108],"joint":[110],"optimization":[111],"for":[112,126,151,159],"network-based":[113],"analysis":[114,149],"deep":[116],"textual":[117],"model":[118,191,243],"training.":[119],"therefore":[121],"propose":[122],"novel":[124],"framework":[125,218],"minimally":[127],"learning":[131,157],"network.":[135],"Specifically,":[136],"jointly":[138],"train":[139],"two":[140,193],"modules":[141,177],"different":[143],"inductive":[144],"biases":[145],"\u2013":[146],"module":[150,158,165],"understanding":[153],"class-discriminative,":[160],"scalable":[161],"learning.":[163],"Each":[164],"generates":[166],"pseudo":[167,186],"training":[168],"labels":[169],"unlabeled":[172],"set,":[174],"both":[176],"mutually":[178],"enhance":[179],"each":[180],"other":[181],"co-training":[183],"using":[184],"pooled":[185],"labels.":[187],"test":[189],"our":[190,206,217,231],"real-world":[194],"datasets.":[195],"On":[196],"challenging":[198],"e-commerce":[199],"product":[200],"dataset":[202],"683":[204],"experiments":[207],"show":[208],"given":[210],"only":[211,234],"three":[212],"category,":[216],"achieve":[220],"accuracy":[222,232],"about":[224,246],"92%,":[225],"significantly":[226],"outperforming":[227],"all":[228],"compared":[229],"methods;":[230],"less":[235],"than":[236],"2%":[237],"away":[238],"BERT":[242],"trained":[244],"50K":[247],"labeled":[248],"documents.":[249]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}