{"id":"https://openalex.org/W3167926051","doi":"https://doi.org/10.1145/3447548.3467215","title":"Domain-oriented Language Modeling with Adaptive Hybrid Masking and Optimal Transport Alignment","display_name":"Domain-oriented Language Modeling with Adaptive Hybrid Masking and Optimal Transport Alignment","publication_year":2021,"publication_date":"2021-08-12","ids":{"openalex":"https://openalex.org/W3167926051","doi":"https://doi.org/10.1145/3447548.3467215","mag":"3167926051"},"language":"en","primary_location":{"id":"doi:10.1145/3447548.3467215","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467215","pdf_url":null,"source":null,"license":null,"license_id":null,"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":"article","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/A5101638181","display_name":"Denghui Zhang","orcid":"https://orcid.org/0000-0002-8452-5925"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Denghui Zhang","raw_affiliation_strings":["Rutgers University, Newark, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Rutgers University, Newark, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049462386","display_name":"Zixuan Yuan","orcid":"https://orcid.org/0000-0003-1197-0347"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zixuan Yuan","raw_affiliation_strings":["Rutgers University, Newark, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Rutgers University, Newark, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101594832","display_name":"Yanchi Liu","orcid":"https://orcid.org/0000-0003-4396-5139"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanchi Liu","raw_affiliation_strings":["NEC Labs America, Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"NEC Labs America, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458897","display_name":"Hao Liu","orcid":"https://orcid.org/0000-0003-4271-1567"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hao Liu","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hongkong, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hongkong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041921496","display_name":"Fuzhen Zhuang","orcid":"https://orcid.org/0000-0001-9170-7009"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuzhen Zhuang","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101862104","display_name":"Hui Xiong","orcid":"https://orcid.org/0000-0001-6016-6465"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hui Xiong","raw_affiliation_strings":["Rutgers University, Newark, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Rutgers University, Newark, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100456776","display_name":"Haifeng Chen","orcid":"https://orcid.org/0000-0002-1318-6583"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haifeng Chen","raw_affiliation_strings":["NEC Labs America, Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"NEC Labs America, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101638181"],"corresponding_institution_ids":["https://openalex.org/I102322142"],"apc_list":null,"apc_paid":null,"fwci":0.5598,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.72756265,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2145","last_page":"2153"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9728999733924866,"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":0.8611763715744019},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.7196399569511414},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7079342007637024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6039329767227173},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5993587374687195},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5347126722335815},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.5135176777839661},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46486955881118774},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3244458734989166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8611763715744019},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7196399569511414},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7079342007637024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6039329767227173},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5993587374687195},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5347126722335815},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.5135176777839661},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46486955881118774},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3244458734989166},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3447548.3467215","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467215","pdf_url":null,"source":null,"license":null,"license_id":null,"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:repository.hkust.edu.hk:1783.1-113212","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=&rft.volume=&rft.issue=&rft.date=2021&rft.spage=2145&rft.aulast=Zhang&rft.aufirst=&rft.atitle=Domain-oriented+Language+Modeling+with+Adaptive+Hybrid+Masking+and+Optimal+Transport+Alignment&rft.title=Proceedings+of+the+ACM+SIGKDD+International+Conference+on+Knowledge+Discovery+and+Data+Mining","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"},{"id":"pmh:oai:repository.ust.hk:1783.1-113212","is_oa":false,"landing_page_url":"http://repository.ust.hk/ir/Record/1783.1-113212","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G6311313454","display_name":null,"funder_award_id":"III-2006387, IIS 1814510, IIS-2040799.","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W385466589","https://openalex.org/W1991418309","https://openalex.org/W2153579005","https://openalex.org/W2158131535","https://openalex.org/W2593560537","https://openalex.org/W2604454537","https://openalex.org/W2739748921","https://openalex.org/W2805680509","https://openalex.org/W2889496895","https://openalex.org/W2911489562","https://openalex.org/W2937845937","https://openalex.org/W2938830017","https://openalex.org/W2952357537","https://openalex.org/W2962739339","https://openalex.org/W2963341956","https://openalex.org/W2963748441","https://openalex.org/W2966645965","https://openalex.org/W2970771982","https://openalex.org/W2971196067","https://openalex.org/W2987154291","https://openalex.org/W2987222756","https://openalex.org/W2996428491","https://openalex.org/W2997200074","https://openalex.org/W3011411500","https://openalex.org/W3030236966","https://openalex.org/W3034220197","https://openalex.org/W3034238904","https://openalex.org/W3034326350","https://openalex.org/W3046375318","https://openalex.org/W3093543164","https://openalex.org/W3099950029","https://openalex.org/W3103223797","https://openalex.org/W3103981637","https://openalex.org/W3149252920"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W2012262991","https://openalex.org/W2373794620","https://openalex.org/W2357294589","https://openalex.org/W2386861027","https://openalex.org/W1583422155","https://openalex.org/W2158321484","https://openalex.org/W3213252596","https://openalex.org/W1649619740","https://openalex.org/W1534006406"],"abstract_inverted_index":{"Motivated":[0],"by":[1,77,95],"the":[2,44,54,82,110,118,133,199,207,230],"success":[3],"of":[4,15,53,64,88,105,112,202,232],"pre-trained":[5,203],"language":[6,17],"models":[7,30,40,90],"such":[8,68,164],"as":[9,152,194],"BERT":[10,46],"in":[11,210],"a":[12,50,103,122,148],"broad":[13],"range":[14],"natural":[16],"processing":[18],"(NLP)":[19],"tasks,":[20],"recent":[21],"research":[22],"efforts":[23],"have":[24,41,49],"been":[25],"made":[26],"for":[27,31],"adapting":[28],"these":[29],"different":[32],"application":[33],"domains.":[34],"Along":[35],"this":[36,211],"line,":[37],"existing":[38,78,134],"domain-oriented":[39,58,124,227],"primarily":[42],"followed":[43],"vanilla":[45],"architecture":[47],"and":[48,67,173,176],"straightforward":[51],"use":[52],"domain":[55,65,129,149],"corpus.":[56],"However,":[57],"tasks":[59,228],"usually":[60],"require":[61],"accurate":[62],"understanding":[63],"phrases,":[66],"fine-grained":[69],"phrase-level":[70],"knowledge":[71,130,144],"is":[72,102],"hard":[73],"to":[74,109,131,141,162,179,190,197,220],"be":[75,92],"captured":[76],"pre-training":[79,89,135],"scheme.":[80],"Also,":[81],"word":[83,171],"co-occurrences":[84],"guided":[85],"semantic":[86,200],"learning":[87,169,172,201],"can":[91],"largely":[93],"augmented":[94],"entity-level":[96],"association":[97,193],"knowledge.":[98,165],"But":[99],"meanwhile,":[100],"there":[101],"risk":[104],"introducing":[106],"noise":[107,209],"due":[108],"lack":[111],"groundtruth":[113],"word-level":[114],"alignment.":[115],"To":[116,205],"address":[117],"issues,":[119],"we":[120,146,156,185,213],"provide":[121],"generalized":[123],"approach,":[125],"which":[126],"leverages":[127],"auxiliary":[128,153],"improve":[132],"framework":[136],"from":[137],"two":[138,168],"aspects.":[139],"First,":[140],"preserve":[142],"phrase":[143,150,174],"effectively,":[145],"build":[147],"pool":[151],"knowledge,":[154],"meanwhile":[155],"introduce":[157,186,214],"Adaptive":[158],"Hybrid":[159],"Masked":[160],"Model":[161],"incorporate":[163],"It":[166],"integrates":[167],"modes,":[170],"learning,":[175],"allows":[177],"them":[178],"switch":[180],"between":[181],"each":[182],"other.":[183],"Second,":[184],"Cross":[187],"Entity":[188],"Alignment":[189],"leverage":[191],"entity":[192],"weak":[195],"supervision":[196],"augment":[198],"models.":[204],"alleviate":[206],"potential":[208],"process,":[212],"an":[215],"interpretableOptimal":[216],"Transport":[217],"based":[218],"approach":[219],"guide":[221],"alignment":[222],"learning.":[223],"Experiments":[224],"on":[225],"four":[226],"demonstrate":[229],"superiority":[231],"our":[233],"framework.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}