{"id":"https://openalex.org/W3167193897","doi":"https://doi.org/10.1145/3447548.3467397","title":"UCPhrase","display_name":"UCPhrase","publication_year":2021,"publication_date":"2021-08-12","ids":{"openalex":"https://openalex.org/W3167193897","doi":"https://doi.org/10.1145/3447548.3467397","mag":"3167193897"},"language":"en","primary_location":{"id":"doi:10.1145/3447548.3467397","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447548.3467397","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467397","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 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467397","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiaotao Gu","orcid":null},"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":"Xiaotao Gu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zihan Wang","orcid":null},"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":"Zihan Wang","raw_affiliation_strings":["University of California, San Diego, San Diago, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego, San Diago, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhenyu Bi","orcid":null},"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":"Zhenyu Bi","raw_affiliation_strings":["University of California, San Diego, San Diago, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego, San Diago, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yu Meng","orcid":null},"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":"Yu Meng","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liyuan Liu","orcid":null},"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":"Liyuan Liu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiawei Han","orcid":null},"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, Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jingbo Shang","orcid":null},"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, San Diago, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego, San Diago, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"478","last_page":"486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":1.0,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":1.0,"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":0.9998000264167786,"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":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.84170001745224},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5343999862670898},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.5210000276565552},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5134999752044678},{"id":"https://openalex.org/keywords/noun-phrase","display_name":"Noun phrase","score":0.5127999782562256},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4345000088214874},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.412200003862381},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.36649999022483826}],"concepts":[{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.84170001745224},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7197999954223633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6741999983787537},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6299999952316284},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5343999862670898},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5210000276565552},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5134999752044678},{"id":"https://openalex.org/C153962237","wikidata":"https://www.wikidata.org/wiki/Q1401131","display_name":"Noun phrase","level":3,"score":0.5127999782562256},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C88880766","wikidata":"https://www.wikidata.org/wiki/Q1201147","display_name":"Determiner phrase","level":4,"score":0.3142000138759613},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C80877019","wikidata":"https://www.wikidata.org/wiki/Q7188074","display_name":"Phrase structure rules","level":3,"score":0.2856999933719635},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.27140000462532043},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3447548.3467397","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447548.3467397","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467397","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 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.14078","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.14078","pdf_url":"https://arxiv.org/pdf/2105.14078","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":"doi:10.1145/3447548.3467397","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447548.3467397","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467397","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 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1472423617","display_name":null,"funder_award_id":"FA8750-19-2-1004","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G1477549303","display_name":null,"funder_award_id":"W911NF-17-C-0099,FA8750-19-2-1004","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G2063335192","display_name":"Molecule Maker Lab Institute (MMLI): An AI Institute for Molecular Discovery, Synthetic Strategy, and Manufacturing","funder_award_id":"2019897","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2104517209","display_name":null,"funder_award_id":"IIS-17-41317","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G427511869","display_name":null,"funder_award_id":"IIS 17-04532","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G449572216","display_name":"NSF Convergence Accelerator Track D: Towards Intelligent Sharing and Search for AI Models and Datasets","funder_award_id":"2040727","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G6445402324","display_name":null,"funder_award_id":"IIS-19-56151","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6821942394","display_name":null,"funder_award_id":"IIS-19-56151,IIS-17-41317,IIS 17-04532,2019897,OIA-2040727","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8175839138","display_name":null,"funder_award_id":"No. W911NF-17-C-0099","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8851674072","display_name":null,"funder_award_id":"W911NF-17-C-0099","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3167193897.pdf","grobid_xml":"https://content.openalex.org/works/W3167193897.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1541542953","https://openalex.org/W2004763266","https://openalex.org/W2020278455","https://openalex.org/W2049107599","https://openalex.org/W2119864770","https://openalex.org/W2123442489","https://openalex.org/W2150815390","https://openalex.org/W2153927559","https://openalex.org/W2162172169","https://openalex.org/W2223881431","https://openalex.org/W2593560537","https://openalex.org/W2888039742","https://openalex.org/W2891383691","https://openalex.org/W2963265326","https://openalex.org/W2972324944","https://openalex.org/W2996726036","https://openalex.org/W3034238904","https://openalex.org/W3038098779","https://openalex.org/W3046517428","https://openalex.org/W3094588044","https://openalex.org/W4251372957","https://openalex.org/W4301881503"],"related_works":[],"abstract_inverted_index":{"Identifying":[0],"and":[1,26,126,136,225,234,248],"understanding":[2],"quality":[3,85,211],"phrases":[4,34,212],"from":[5,97,168],"context":[6],"is":[7],"a":[8,81,142,169,181,196],"fundamental":[9],"task":[10,20],"in":[11,23,49,122,132,180],"text":[12],"mining.":[13],"The":[14,29],"most":[15],"challenging":[16],"part":[17],"of":[18,32,39,154,214,241],"this":[19,76],"arguably":[21],"lies":[22],"uncommon,":[24],"emerging,":[25,138],"domain-specific":[27],"phrases.":[28,140],"infrequent":[30],"nature":[31],"these":[33],"significantly":[35],"hurts":[36],"the":[37,50,123,152,163,176,191,239],"performance":[38],"phrase":[40,47,86,92,156,229,236],"mining":[41],"methods":[42],"that":[43,162],"rely":[44,62],"on":[45,63,112,147,222],"sufficient":[46],"occurrences":[48],"input":[51,124,207],"corpus.":[52],"Context-aware":[53],"tagging":[54],"models,":[55],"though":[56],"not":[57],"restricted":[58],"by":[59],"frequency,":[60],"heavily":[61],"domain":[64,125],"experts":[65],"for":[66],"either":[67],"massive":[68],"sentence-level":[69,235],"gold":[70],"labels":[71,96,119,149,193],"or":[72,218],"handcrafted":[73],"gazetteers.":[74],"In":[75],"work,":[77],"we":[78,89,160,185],"propose":[79],"UCPhrase,":[80],"novel":[82],"unsupervised":[83],"context-aware":[84],"tagger.":[87],"Specifically,":[88],"induce":[90],"high-quality":[91],"spans":[93],"as":[94],"silver":[95,118,148,192],"consistently":[98],"co-occurring":[99],"word":[100],"sequences":[101],"within":[102],"each":[103],"document.":[104],"Compared":[105],"with":[106,190],"typical":[107],"context-agnostic":[108],"distant":[109],"supervision":[110],"based":[111,146],"existing":[113],"knowledge":[114],"bases":[115],"(KBs),":[116],"our":[117,242],"root":[120],"deeply":[121],"context,":[127],"thus":[128],"having":[129],"unique":[130],"advantages":[131],"preserving":[133],"contextual":[134],"completeness":[135],"capturing":[137],"out-of-KB":[139],"Training":[141],"conventional":[143],"neural":[144,171],"tagger":[145],"usually":[150],"faces":[151],"risk":[153],"overfitting":[155],"surface":[157,216],"names.":[158],"Alternatively,":[159],"observe":[161],"contextualized":[164],"attention":[165,188],"maps":[166,189],"generated":[167],"transformer-based":[170],"language":[172],"model":[173],"effectively":[174],"reveal":[175],"connections":[177],"between":[178],"words":[179],"surface-agnostic":[182],"way.":[183],"Therefore,":[184],"pair":[186],"such":[187],"to":[194,205,208],"train":[195],"lightweight":[197],"span":[198],"prediction":[199],"model,":[200],"which":[201],"can":[202],"be":[203],"applied":[204],"new":[206],"recognize":[209],"(unseen)":[210],"regardless":[213],"their":[215],"names":[217],"frequency.":[219],"Thorough":[220],"experiments":[221],"various":[223],"tasks":[224],"datasets,":[226],"including":[227],"corpus-level":[228],"ranking,":[230],"document-level":[231],"keyphrase":[232],"extraction,":[233],"tagging,":[237],"demonstrate":[238],"superiority":[240],"design":[243],"over":[244],"state-of-the-art":[245],"pre-trained,":[246],"unsupervised,":[247],"distantly":[249],"supervised":[250],"methods.":[251]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-06-22T00:00:00"}